Invest Verify Remediation logo

Invest Verify Remediation

Community
erikaflowers
invest-verify-remediation

After a remediation plan has been executed, verify that findings were resolved without introducing new issues. Updates AUDIT.md with resolution status, cleans up REMEDIATION.md, and confirms the codebase is ready to resume building.

Overview

Publishererikaflowers
Repositoryinvestiture
Skill nameinvest-verify-remediation
Stars
55
Forks
9
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Invest Verify Remediation 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.
    https://github.com/erikaflowers/investiture/tree/main/.claude/skills/invest-verify-remediation
  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/erikaflowers/investiture.git /tmp/investiture
mkdir -p .claude/skills
cp -r /tmp/investiture/.claude/skills/invest-verify-remediation .claude/skills/invest-verify-remediation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Invest Verify Remediation 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 Invest Verify Remediation 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 Invest Verify Remediation 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.

Verify Remediation

You are verifying that a remediation plan was executed correctly. You are not re-auditing the entire codebase — you are checking the specific files that were changed, confirming findings are resolved, and flagging anything new that was introduced.

This is a focused re-scan, not a full audit. Speed matters. 10-15 minutes, not an hour.

Target

The codebase at $ARGUMENTS. If no argument is provided, use the current working directory.

Prerequisites

  • AUDIT.md must exist in the repo root (from a prior /invest-repo-audit)
  • REMEDIATION.md must exist in the repo root (from a prior /invest-remediate)
  • The remediation phases must have been executed (commits exist)

Process

1. Identify what changed

Read REMEDIATION.md to understand what phases were planned. Then check git history to see what was actually done:

bash
# Find commits since the remediation plan was created
git log --oneline --since="$(git log --format='%ai' -- REMEDIATION.md | head -1)" -- . ':!MANIFEST.md' ':!AUDIT.md' ':!REMEDIATION.md'

Build a list of every file that was modified, created, or deleted as part of remediation.

2. Verify each finding

Read AUDIT.md. For every finding (Critical, Significant, Minor):

If the finding was addressed by a remediation phase:

  • Read the modified file(s)
  • Confirm the fix matches what REMEDIATION.md specified
  • Check that the fix doesn't introduce new issues (e.g., an extracted component missing an import, a split file with broken references)
  • Mark as RESOLVED

If the finding was explicitly deferred in REMEDIATION.md ("What This Plan Does NOT Cover"):

  • Confirm it is still present (not accidentally fixed or worsened)
  • Mark as DEFERRED with brief reason from REMEDIATION.md

If the finding was in a remediation phase but NOT addressed:

  • Confirm it is still present
  • Mark as OPEN

3. Check for regressions

For every file that was modified during remediation:

  • Does it still build? (Run npm run build or equivalent)
  • Are there new lint errors?
  • Are there new files over 500 lines?
  • Are there new functions over 80 lines?
  • Did the fix introduce any patterns the original audit flagged as problems? (e.g., fixing one god file by creating another)

4. Check for orphaned artifacts

  • Are there any new unused imports?
  • If files were split (e.g., tool-registry), do all consumers import from the new locations?
  • If files were deleted, are there any dangling references?

5. Update AUDIT.md

Rewrite AUDIT.md in place with resolution status. Keep the exact same structure but add status to each finding:

For resolved findings, update the heading:

markdown
### C1. tool-registry.mjs — 1065-Line God File — RESOLVED

Add a resolution note at the end of the finding:

markdown
**Resolution:** Split into 7 files in `netlify/functions/lib/tools/`. Aggregator at `tools/index.mjs` maintains same export API. Commit: [hash]. Verified: imports updated, build passes, tool execution confirmed.

For deferred findings:

markdown
### S9. useAuth.jsx — Token Refresh Race Condition — DEFERRED

Add:

markdown
**Status:** Deferred — requires auth flow redesign, scoped as separate initiative.

For open findings (should have been fixed but weren't):

markdown
### S6. Stale Stream Auto-Resolution Race Condition — OPEN

Add:

markdown
**Status:** Open — not addressed in remediation. Original finding still applies.

Update the Summary Metrics table to include resolution counts:

markdown
| Metric | Count |
|--------|-------|
| Files audited | 137 |
| Critical findings | 3 (X resolved, Y deferred, Z open) |
| Significant findings | 10 (X resolved, Y deferred, Z open) |
| Minor findings | 8 (X resolved, Y deferred, Z open) |

Update the overall classification if warranted. If all critical findings are resolved and most significant findings are resolved, the classification may improve (e.g., SIGNIFICANT DEBT → MINOR DEBT).

6. Clean up REMEDIATION.md

Delete REMEDIATION.md from the repo. It has served its purpose. The resolution status now lives in AUDIT.md. Keeping both creates confusion about what's current.

7. Verify MANIFEST.md accuracy

Spot-check MANIFEST.md against the changes:

  • If files were added, are they in the manifest?
  • If files were deleted, are they removed from the manifest?
  • If files were renamed or split, is the manifest updated?

If MANIFEST.md is stale, update it to reflect the current state. Do NOT re-run a full manifest — just patch the sections that changed.

Output Format

Output directly to the conversation (do NOT write a separate report file):

VERIFICATION COMPLETE
═══════════════════════════════════════════════════════════════

Remediation phases executed: [N of M]
Files modified: [count]
Files created: [count]
Files deleted: [count]

Findings resolved: [count]
Findings deferred: [count]
Findings still open: [count]

Regressions detected: [count, or "None"]
New issues introduced: [count, or "None"]

Classification change: [OLD] → [NEW] (or "No change")

AUDIT.md: Updated with resolution status
REMEDIATION.md: Deleted
MANIFEST.md: [Updated / Already current / Needs manual update]

Build status: [passes / fails — details if fails]

Verdict: [CLEAR TO RESUME BUILDING | ISSUES REMAIN — details]
═══════════════════════════════════════════════════════════════

Commit

After updating AUDIT.md and deleting REMEDIATION.md:

docs: verify remediation — [N] findings resolved, classification [OLD] → [NEW]

Rules

  • Do NOT re-audit the entire codebase. Only check files that changed and findings that were targeted.
  • Do NOT fix anything. If you find a regression or new issue, report it. Do not repair it. Your job is to verify, not to build.
  • Be honest about partial completion. If only 4 of 6 phases were executed, report that clearly. Do not mark unexecuted phases as resolved.
  • Trust the build. If npm run build passes and the modified files look correct, that's sufficient. Do not invent hypothetical failure scenarios.
  • Keep the updated AUDIT.md concise. Add resolution notes, don't rewrite findings. The original finding text stays — you're adding status, not replacing content.

Frequently asked questions

What does the Invest Verify Remediation AI skill do?

After a remediation plan has been executed, verify that findings were resolved without introducing new issues. Updates AUDIT.md with resolution status, cleans up REMEDIATION.md, and confirms the codebase is ready to resume building.

Why use Invest Verify Remediation on TypingMind?

Because you install it once and use it with any model. Invest Verify Remediation 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 Invest Verify Remediation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/erikaflowers/investiture/tree/main/.claude/skills/invest-verify-remediation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Invest Verify Remediation?

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 Invest Verify Remediation?

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

Is the Invest Verify Remediation AI skill free?

It is published on GitHub by erikaflowers. Check the repository for licensing terms. 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 👇