Status logo

Status

CommunityPopular
jeremylongshore
status

Use when the user wants a one-screen view of current hyperflow project state — version, profile freshness, memory count, and live progress on every in-flight task. Read-only; never modifies state, never dispatches workers. Trigger with /hyperflow:status, "what is hyperflow doing", "show task progress", "where are we".

Overview

Publisherjeremylongshore
Repositorytons-of-skills-marketplace
Skill namestatus
Stars
2.8K
Forks
402
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jeremylongshore on GitHub. Read the source before you install it.

Installation

Install the Status AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace
mkdir -p .claude/skills
cp -r /tmp/tons-of-skills-marketplace/plugins/ai-agency/hyperflow/skills/status .claude/skills/status
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Status in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Status on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Status is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Status

Read-only snapshot of the current hyperflow project, with live progress on every active task file. Standalone — does not auto-chain and is never invoked by other skills. Invoked manually via /hyperflow:status.

The skill has two sections:

  1. Static snapshot — version, profile freshness, memory count
  2. In-flight work — per-task live progress (sub-tasks done/total, tokens, wall-clock, ETA)

What to read

Static snapshot

FieldSourceFallback
VersionLatest git tag matching v* + tag commit date(missing)
Profile.hyperflow/profile.md file modification time(missing)
MemoryLine count of .hyperflow/memory/index.md minus header rows(none)
Active tasksFiles matching .hyperflow/tasks/*.md(none)
Active featuresFolders matching .hyperflow/features/*/feature.md(none)

Active features (multi-phase work)

For every .hyperflow/features/*/feature.md (see feature-phases.md), parse its ## Status block and the phase roster, then for each phase-<n>-*/phase.md show the phase status + Progress bar:

── Feature: checkout-redesign ──  (2 / 3 phases)
  ✓ phase-1-data-layer   completed
  ▸ phase-2-api          in_progress  ████░░░░  2/5 tasks · running: T3-handlers
    phase-3-ui           pending      depends on phase-2

The per-phase bar uses the same parsing as the per-task-file section below (each phase.md carries the same ## Status block shape). Omit this section when no .hyperflow/features/*/ exist.

In-flight work (per task file)

For every .hyperflow/tasks/*.md, parse its ## Status block (written by /hyperflow:plan at creation and updated by /hyperflow:dispatch after each sub-task PASS — see plan/SKILL.md Step 10):

FieldSourceBehaviour
Slugbasename of the task file minus .mdalways present
Done / totalSub-tasks: <done> / <total> from Status blockfalls back to counting [x] vs [x]+[ ] checkboxes if Status missing
Done sub-task nameslines with [x] from the ## Batches sectionlisted under the bar
Running sub-taskthe first [~] checkbox (dispatch marks ~ while a sub-task is mid-flight)(idle) if none
Pending sub-task countcount of [ ] checkboxesshown as N pending
Tokens usedTokens used: line from Status block(not tracked yet) if Status absent
Wall-clockWall-clock: line from Status block(not started) if no Started:
ETAETA: line from Status block(computing) if <3 sub-tasks done

How to compute each field

Version

bash
tag=$(git tag --sort=-v:refname | grep -E '^v[0-9]' | head -1)
released=$(git log -1 --format=%ci "$tag" 2>/dev/null | cut -d' ' -f1)

If $tag is empty → print (missing).

Profile freshness

bash
profile=".hyperflow/profile.md"
now=$(date +%s)
mtime=$(stat -f %m "$profile" 2>/dev/null || stat -c %Y "$profile" 2>/dev/null)
hours=$(( (now - mtime) / 3600 ))
  • File absent → (missing)
  • hours <= 24fresh (analyzed Xh ago)
  • hours > 24stale (analyzed Xh ago)

Memory entry count

Count table-body rows in .hyperflow/memory/index.md (lines starting with |, minus header + separator):

bash
count=$(grep -c '^|' .hyperflow/memory/index.md 2>/dev/null)
entries=$(( count - 2 ))

If file absent or count ≤ 0 → (none).

Active tasks list

bash
tasks=$(ls .hyperflow/tasks/*.md 2>/dev/null)

If no files → show (none) and skip the In-flight section entirely.

Per-task Status parsing

For each .hyperflow/tasks/<slug>.md:

bash
# Extract Status block fields
sub_done=$(grep '^Sub-tasks:' "$file" | sed -E 's|.*: *([0-9]+) */ *([0-9]+).*|\1|')
sub_total=$(grep '^Sub-tasks:' "$file" | sed -E 's|.*: *([0-9]+) */ *([0-9]+).*|\2|')
tokens=$(grep '^Tokens used:' "$file" | sed 's|^Tokens used: *||')
wall=$(grep '^Wall-clock:' "$file" | sed 's|^Wall-clock: *||')
eta=$(grep '^ETA:' "$file" | sed 's|^ETA: *||')
started=$(grep '^Started:' "$file" | sed 's|^Started: *||')

If the Status block is missing or malformed (old-style task file from before this format), fall back to counting checkboxes directly:

bash
done=$(grep -c '^- \[x\]' "$file" 2>/dev/null)
running=$(grep -c '^- \[~\]' "$file" 2>/dev/null)
pending=$(grep -c '^- \[ \]' "$file" 2>/dev/null)
total=$(( done + running + pending ))

Done sub-task names (for the indented list)

bash
grep '^- \[x\]' "$file" | sed -E 's|^- \[x\] *||' | head -5

Show up to the last 3 completed + the currently running sub-task. If there are more than 3 done, prefix the list with … (N earlier done).

Running sub-task

The dispatch skill marks the in-flight sub-task with [~] while the worker is running. After PASS + commit, dispatch flips [~][x].

bash
running=$(grep '^- \[~\]' "$file" | sed -E 's|^- \[~\] *||' | head -1)

If no [~] line exists → the dispatch is either between sub-tasks (idle for milliseconds) or has handed control back. Show (idle — last update Xm Ys ago) based on Last update: timestamp.

Progress bar

20-char ASCII bar based on done / total:

[████████████░░░░░░░░] 12/20  60%

Use (filled) and (empty). No emoji or color icons.

Output format

Print the block below verbatim. If no in-flight tasks, omit the ── In-flight work ── section.

── Hyperflow Status ─────────────────────────────────────────
Version       v3.0.0     (released 2026-05-16)
Profile       fresh      (analyzed 2h ago)
Memory        12 entries
Active tasks  2

── In-flight work ───────────────────────────────────────────
Task:         implement-auth
  Progress    [███████████░░░░░░░░░] 8/14  57%
  Last done   T7: Reset email worker
  Running     T8: Login UI (Implementer · 14s elapsed)
  Pending     6 sub-tasks
  Tokens      thinking 89.2k · worker 142.0k · total 231.2k
  Wall-clock  4m 22s elapsed
  ETA         ~3m 16s remaining   (avg 32s/sub-task · 6 left)

Task:         fix-login-bug
  Progress    [░░░░░░░░░░░░░░░░░░░░] 0/3   0%
  Status      not started (created 8m ago, no dispatch run yet)
─────────────────────────────────────────────────────────────

When Profile is (missing), omit the (analyzed Xh ago) parenthetical.

When Version is (missing), print Version (missing).

When no .hyperflow/tasks/*.md files exist, omit the ── In-flight work ── section entirely; the snapshot block stands alone.

ETA computation

elapsed_seconds       = now - started_unix
avg_per_subtask       = elapsed_seconds / done
remaining_seconds     = avg_per_subtask * pending

Format as Xm Ys or Hh Mm (skip zero leading units). Show (computing) when done < 3 — too few data points for a useful average.

If the task has multiple batches and the next batch is sequential per the planner output, multiply remaining by 1.1 to account for inter-batch synchronisation overhead.

Failure modes

Every section degrades gracefully:

  • Missing git tags → Version (missing)
  • Missing .hyperflow/profile.mdProfile (missing)
  • Missing .hyperflow/memory/index.mdMemory (none)
  • No .hyperflow/tasks/*.md files → Active tasks (none), no In-flight section
  • Task file present but Status block malformed/missing → fall back to checkbox count, show (not tracked yet) for tokens/ETA
  • Started: line absent → Status not started, skip ETA

Never error out. Never modify any file. Never dispatch an agent.

Doctrine

This skill has no Worker/Reviewer dispatch — it is a pure read. It does not count as a hyperflow run and does not append to memory. Output style follows output-style.md — no decorative icons, em-dash separators, plain status words.

Overview

/hyperflow:status prints a one-screen snapshot of the project's hyperflow state plus a live progress block for every in-flight task. Useful when picking up a session mid-flight, deciding whether to invoke /hyperflow:dispatch, or auditing whether a chain run is still healthy. Pure read — no agents, no writes, no chain side-effects.

Prerequisites

  • Git repository (for the version line — degrades to (missing) otherwise).
  • .hyperflow/ directory (for profile/memory/tasks lines — each section degrades to (missing) or (none) if absent).
  • No prerequisites for invocation itself — runs anywhere.

Instructions

See What to read and How to compute each field above for the full operational spec. Summary:

  1. Read version from latest git tag matching v*.
  2. Stat .hyperflow/profile.md for freshness; bucket into fresh/stale/missing.
  3. Count entries in .hyperflow/memory/index.md.
  4. Glob .hyperflow/tasks/*.md and parse each Status block for live progress.
  5. Render the static snapshot block; render the In-flight block per task (if any).
  6. Stop. No prompts, no follow-ups.

Output

See Output format above for the exact block. Two sections — static snapshot and (if there are active tasks) In-flight work with per-task progress bar, last-done sub-task, currently-running sub-task, pending count, tokens, wall-clock, ETA.

Error Handling

FailureBehavior
Not a git repoVersion (missing); everything else still renders if .hyperflow/ exists.
.hyperflow/profile.md missingProfile (missing) (no parenthetical).
.hyperflow/memory/index.md missingMemory (none).
No task filesOmit the In-flight section entirely; just print the snapshot.
Task file with malformed Status blockFall back to counting [x] vs [ ] checkboxes; show (not tracked yet) for tokens/ETA.
stat flag differs between BSD (macOS) and GNU (Linux)Try stat -f %m then fall back to stat -c %Y.

Never errors out. Never modifies any file. Never dispatches an agent.

Examples

Healthy project, no active tasks

── Hyperflow Status ─────────────────────────────────────────
Version       v3.1.2     (released 2026-05-16)
Profile       fresh      (analyzed 2h ago)
Memory        12 entries
Active tasks  (none)
─────────────────────────────────────────────────────────────

Mid-dispatch with two active tasks

── Hyperflow Status ─────────────────────────────────────────
Version       v3.1.2     (released 2026-05-16)
Profile       fresh      (analyzed 2h ago)
Memory        12 entries
Active tasks  2

── In-flight work ───────────────────────────────────────────
Task:         implement-auth
  Progress    [███████████░░░░░░░░░] 8/14  57%
  Last done   T7: Reset email worker
  Running     T8: Login UI (Implementer · 14s elapsed)
  Pending     6 sub-tasks
  Tokens      thinking 89.2k · worker 142.0k · total 231.2k
  Wall-clock  4m 22s elapsed
  ETA         ~3m 16s remaining   (avg 32s/sub-task · 6 left)

Task:         fix-login-bug
  Progress    [░░░░░░░░░░░░░░░░░░░░] 0/3   0%
  Status      not started (created 8m ago, no dispatch run yet)
─────────────────────────────────────────────────────────────

Brand new install (no .hyperflow/ yet)

── Hyperflow Status ─────────────────────────────────────────
Version       v3.1.2     (released 2026-05-16)
Profile       (missing)
Memory        (none)
Active tasks  (none)
─────────────────────────────────────────────────────────────

Resources

  • output-style.md — em-dash style, no decorative chars, plain status words.
  • DOCTRINE.md — orchestration rules (status is exempt from per-step agent dispatch).

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Status AI skill do?

Use when the user wants a one-screen view of current hyperflow project state — version, profile freshness, memory count, and live progress on every in-flight task. Read-only; never modifies state, never dispatches workers. Trigger with /hyperflow:status, "what is hyperflow doing", "show task progress", "where are we".

Why use Status on TypingMind?

Because you install it once and use it with any model. Status is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Status in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/hyperflow/skills/status. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Status?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Status?

As many as you like. As long as a model supports skills, you can use Status with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Status AI skill free?

Yes. It is published on GitHub by jeremylongshore under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇