Pp Catapult Openfield Connect

Catapult OpenField — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the catapult-openfield-connect-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   bashCopy code
   npx -y @mvanhorn/printing-press-library install catapult-openfield-connect --cli-only
   

2. Verify: catapult-openfield-connect-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.5 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

bashCopy code
go install github.com/mvanhorn/printing-press-library/library/health/catapult-openfield-connect/cmd/catapult-openfield-connect-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

catapult-openfield-connect-pp-cli syncs your OpenField data into a local SQLite store and unlocks computations the API cannot do alone: 28-day ACWR dashboards, personal velocity bests, session diffs, and positional benchmarks — all scriptable, pipeable, and agent-native. What used to require a custom R script now takes one command.

When to Use This CLI

Use this CLI for any Catapult OpenField data task: pulling session stats, checking squad ACWR, comparing matches, generating load reports, or giving an agent access to athlete GPS data without manual OpenField exports. It is the only CLI surface for OpenField; the alternative is the catapultR R package or the web UI.

Anti-triggers

Do not use this CLI for:

• Do not use this CLI to create, update, or delete anything in OpenField — it is read-only by design
• Do not use it for live in-session streaming telemetry; it reads completed activity data
• Do not use it for video or tactical analysis — OpenField carries GPS/accelerometer data only

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Load intelligence that compounds

• acwr — Instant acute:chronic workload ratios for any athlete or the full squad, color-coded into safe (0.8-1.3), caution, and danger (>1.5) zones.

  Reach for this when asked who is at injury risk or for the morning workload check.

  bashCopy code
  catapult-openfield-connect-pp-cli acwr --squad --metric total_player_load --flag-risk --agent
  

• report — One-command weekly summary — total Player Load, session count, ACWR, max velocity vs PB, monotony, strain, and risk flags — exportable as markdown or CSV.

  Reach for this when a coach briefing or weekly load summary is requested.

  bashCopy code
  catapult-openfield-connect-pp-cli report --week --squad --format markdown --export ./week_load.md
  

• pb — Compares recent session values against each athlete's all-time or rolling personal best, with readiness % and 3-session trend arrows.

  Use before deciding who trains at full intensity today.

  bashCopy code
  catapult-openfield-connect-pp-cli pb --metric max_vel --vs-peak --agent
  

• benchmark — Ranks any athlete against positional peers for a metric: percentile rank, squad median, and position median with outlier flags.

  Use after match debriefs to answer how an athlete compares to peers.

  bashCopy code
  catapult-openfield-connect-pp-cli benchmark --metric total_distance --percentile --agent
  

Session analysis

• diff — Side-by-side comparison of two sessions (by ID, date, or last/prev) showing absolute and percentage change per metric and per athlete.

  Use to diagnose travel fatigue and fixture congestion between consecutive matches.

  bashCopy code
  catapult-openfield-connect-pp-cli diff last prev --squad --metrics total_player_load,max_vel --agent
  

• rtp — Tracks an injured athlete's load progression session-by-session as a percentage of squad average or a pre-injury baseline window.

  Use when managing return-to-play decisions to give medical staff quantitative progression data.

  bashCopy code
  catapult-openfield-connect-pp-cli rtp --athlete top --target-metric total_player_load --vs-squad --threshold 85 --agent
  

• heatmap — Renders an athlete-by-period intensity matrix for a session — ANSI heatmap on a terminal, JSON matrix for agents — surfacing where fatigue compounded.

  Use after matches to diagnose second-half performance drops.

  bashCopy code
  catapult-openfield-connect-pp-cli heatmap --activity last --metric total_player_load --json
  

Command Reference

activities — Training sessions and matches

• catapult-openfield-connect-pp-cli activities annotations — Annotations on an activity
• catapult-openfield-connect-pp-cli activities athletes — Athletes who participated in an activity
• catapult-openfield-connect-pp-cli activities devices — Devices used in an activity
• catapult-openfield-connect-pp-cli activities get — Get one activity; use --embed all for tag/athlete detail
• catapult-openfield-connect-pp-cli activities list — List activities (sessions and matches) with venue and timing
• catapult-openfield-connect-pp-cli activities periods — Periods (halves, quarters, drills) within an activity

annotations — Annotation metadata

• catapult-openfield-connect-pp-cli annotations — List annotation categories

athletes — Athletes registered in the OpenField account

• catapult-openfield-connect-pp-cli athletes annotations — Annotations recorded against an athlete
• catapult-openfield-connect-pp-cli athletes bands — Velocity/acceleration band thresholds configured for an athlete
• catapult-openfield-connect-pp-cli athletes list — List all athletes with physical attributes, jersey numbers, and positions

customer — Account info and settings

• catapult-openfield-connect-pp-cli customer get — Customer account info
• catapult-openfield-connect-pp-cli customer settings — User settings including velocity and distance units

parameters — The 200+ metric catalog (Player Load, banded velocity, heart rate...)

• catapult-openfield-connect-pp-cli parameters — List every parameter (metric) available in OpenField, with slugs used by stats queries

periods — Periods across activities

• catapult-openfield-connect-pp-cli periods annotations — Annotations on a period
• catapult-openfield-connect-pp-cli periods athletes — Athletes in a period

sensor — Raw 10Hz sensor data, IMA events, and velocity/acceleration efforts

• catapult-openfield-connect-pp-cli sensor data — 10Hz sensor stream for one athlete in one activity (large; requires sensor-read-only scope)
• catapult-openfield-connect-pp-cli sensor efforts — Generation-2 velocity or acceleration efforts for one athlete in one activity
• catapult-openfield-connect-pp-cli sensor events — IMA events (jumps, dives, sport-specific movements) for one athlete in one activity

stats — The stats query engine — computed metrics with grouping and filters

• catapult-openfield-connect-pp-cli stats — Query computed statistics.

teams — Teams in the account

• catapult-openfield-connect-pp-cli teams — List teams

venues — Venues

• catapult-openfield-connect-pp-cli venues get — Get one venue
• catapult-openfield-connect-pp-cli venues list — List venues

Freshness Contract

This printed CLI owns bounded freshness only for registered store-backed read command paths. In --data-source auto mode, those paths check sync_state and may run a bounded refresh before reading local data. --data-source local never refreshes. --data-source live reads the API and does not mutate the local store. Set CATAPULT_OPENFIELD_CONNECT_NO_AUTO_REFRESH=1 to skip the freshness hook without changing source selection.

Covered paths:

• catapult-openfield-connect-pp-cli activities
• catapult-openfield-connect-pp-cli activities list
• catapult-openfield-connect-pp-cli annotations
• catapult-openfield-connect-pp-cli athletes
• catapult-openfield-connect-pp-cli athletes list
• catapult-openfield-connect-pp-cli parameters
• catapult-openfield-connect-pp-cli sensor
• catapult-openfield-connect-pp-cli teams
• catapult-openfield-connect-pp-cli venues
• catapult-openfield-connect-pp-cli venues list
• catapult-openfield-connect-pp-cli customer
• catapult-openfield-connect-pp-cli customer get
• catapult-openfield-connect-pp-cli customer settings

When JSON output uses the generated provenance envelope, freshness metadata appears at meta.freshness. Treat it as current-cache freshness for the covered command path, not a guarantee of complete historical backfill or API-specific enrichment.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bashCopy code
catapult-openfield-connect-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Recipes

Morning ACWR check for the full squad

bashCopy code
catapult-openfield-connect-pp-cli acwr --squad --flag-risk --agent --select athlete_name,acwr,risk_zone

Run before every training session to see who is in the caution or danger zone.

Post-session stats grouped by athlete

bashCopy code
catapult-openfield-connect-pp-cli stats --parameters total_player_load,total_distance,max_vel --group-by athlete --json

The primary data pull after every session.

Compare the last two matches

bashCopy code
catapult-openfield-connect-pp-cli diff last prev --squad --metrics total_player_load,max_vel --agent --select athlete_name,metric,delta_pct

Percentage change per athlete per metric between matches; --select keeps agent context tight.

Find velocity metric slugs

bashCopy code
catapult-openfield-connect-pp-cli search "velocity" --type parameters --limit 10

Discover exact slugs before building a stats query.

Weekly report to markdown

bashCopy code
catapult-openfield-connect-pp-cli report --week --squad --format markdown --export ./week12_load.md

Paste directly into the coach briefing doc.

Auth Setup

OpenField Connect accepts a long-lived API token (create one in OpenField under API Tokens) sent as a Bearer header. Set CATAPULT_TOKEN in your environment or run auth set-token. Regional hosts differ: this CLI defaults to the Americas host (us.catapultsports.com); override base_url in config for APAC/EMEA tenants.

Run catapult-openfield-connect-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  bashCopy code
  catapult-openfield-connect-pp-cli activities list --agent --select id,name,status
  

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• Non-interactive — never prompts, every input is a flag

• Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

jsonCopy code
{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set CATAPULT_OPENFIELD_CONNECT_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: CATAPULT_OPENFIELD_CONNECT_CONFIG_DIR, CATAPULT_OPENFIELD_CONNECT_DATA_DIR, CATAPULT_OPENFIELD_CONNECT_STATE_DIR, CATAPULT_OPENFIELD_CONNECT_CACHE_DIR.

• Resolution order is per-kind env var, --home, CATAPULT_OPENFIELD_CONNECT_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

• config contains settings like config.toml and profiles. data contains credentials.toml, data.db, cookies, and auth sidecars. state contains persisted queries, jobs, and teach.log. cache contains regenerable HTTP/cache files.

• Stored secrets live in credentials.toml under the data dir. Existing legacy config.toml secrets are read for compatibility and leave config.toml on the first auth write.

• Run catapult-openfield-connect-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

• For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

  jsonCopy code
  {
    "mcpServers": {
      "catapult-openfield-connect": {
        "command": "catapult-openfield-connect-pp-mcp",
        "env": {
          "CATAPULT_OPENFIELD_CONNECT_HOME": "/srv/catapult-openfield-connect"
        }
      }
    }
  }
  

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use CATAPULT_OPENFIELD_CONNECT_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing CATAPULT_OPENFIELD_CONNECT_HOME, or doctor will not find credentials left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, run:

bashCopy code
catapult-openfield-connect-pp-cli recall "<user's question>" --agent

The response envelope:

jsonCopy code
{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "catapult-openfield-connect-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

Copy code
if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `catapult-openfield-connect-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; catapult-openfield-connect-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Step 3: always read warnings

• low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
• resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
• cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
• similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
• ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
• candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
• lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run catapult-openfield-connect-pp-cli sync to refresh entity lookups.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.

Step 4: teach & after finalizing your response - always

Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell & so the call returns immediately:

bashCopy code
catapult-openfield-connect-pp-cli teach --query "<user's question>" --resource-type <type> --resource <id1> --resource <id2>
# (append shell `&` to background it)

Silent on success. Errors only land in teach.log under the resolved state dir. Teach the most specific resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded entity_lookups for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically.

PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning.

Step 5: playbooks - optional flags, automatic synthesis

You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a playbook_candidate from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the integrated one-call form - record the resource learning and the playbook in the same teach invocation:

bashCopy code
# Common case: record both the resource learning AND the playbook in one call.
catapult-openfield-connect-pp-cli teach \
  --query "<user's question>" \
  --resource <id> \
  --playbook-file ~/playbooks/<shape>.json \
  --playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)

# Alternate: playbook-only (no resource to record alongside).
catapult-openfield-connect-pp-cli teach-playbook \
  --query "<user's question>" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-notes.md

Playbook files are JSON with steps, entity_slots, expected_tool_calls. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: --playbook-json and --playbook-notes on the integrated teach form, --playbook-json and --notes on teach-playbook. On the integrated teach form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone teach-playbook form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with slots_resolved binding the live query's canonical at recall time.

When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with slots_resolved substitutions, skip the discovery that the choreography already documents, and read notes before any step.

Step 6: playbook amend & when your debug response identifies a correction

If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire playbook amend BEFORE emitting your user-facing response. Same fire-and-forget posture as teach.

bashCopy code
catapult-openfield-connect-pp-cli playbook amend \
  --query "<exact recall query string>" \
  --add-note "<your concrete correction>"
# (append shell `&` to background it)

What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending:

• A workaround for a CLI surface that silently drops or misorders a flag.
• An undocumented endpoint shape (response wrapped in {meta, results}, payload nested two levels deeper than the docs claim).
• Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased).

What does NOT belong in notes:

• The year-specific or entity-specific answer to the user's question. That's the response, not a learning.
• Per-team / per-athlete / per-row data the playbook already retrieves at runtime.
• Statements that paraphrase what the existing notes already say.

The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land).

PII discipline for amend notes

playbook amend notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing:

• Do NOT embed paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user.
• Acceptable: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics.

If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.

Measuring the loop

catapult-openfield-connect-pp-cli learnings stats reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local learn_events table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI.

Disabling learning

• --no-learn on a single command short-circuits both recall and the teach write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings.
• CATAPULT_OPENFIELD_CONNECT_NO_LEARN=true in the environment globally disables the pipeline.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

Copy code
catapult-openfield-connect-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
catapult-openfield-connect-pp-cli feedback --stdin < notes.txt
catapult-openfield-connect-pp-cli feedback list --json --limit 10

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless CATAPULT_OPENFIELD_CONNECT_FEEDBACK_ENDPOINT is set AND either --send is passed or CATAPULT_OPENFIELD_CONNECT_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.

Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.

Output Delivery

Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:

Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run.

Copy code
catapult-openfield-connect-pp-cli profile save briefing --json
catapult-openfield-connect-pp-cli --profile briefing activities list
catapult-openfield-connect-pp-cli profile list --json
catapult-openfield-connect-pp-cli profile show briefing
catapult-openfield-connect-pp-cli profile delete briefing --yes

Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.

Exit Codes

Argument Parsing

Parse $ARGUMENTS:

1. Empty, help, or --help → show catapult-openfield-connect-pp-cli --help output
2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

1. Install the MCP server:

   bashCopy code
   go install github.com/mvanhorn/printing-press-library/library/health/catapult-openfield-connect/cmd/catapult-openfield-connect-pp-mcp@latest
   

2. Register with Claude Code:

   bashCopy code
   claude mcp add catapult-openfield-connect-pp-mcp -- catapult-openfield-connect-pp-mcp
   

3. Verify: claude mcp list

Direct Use

1. Check if installed: which catapult-openfield-connect-pp-cli If not found, offer to install (see Prerequisites at the top of this skill).
2. Match the user query to the best command from the Unique Capabilities and Command Reference above.
3. Execute with the --agent flag:

   bashCopy code
   catapult-openfield-connect-pp-cli acwr --squad --flag-risk --agent
   

4. If ambiguous, drill into subcommand help: catapult-openfield-connect-pp-cli activities --help.