Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/yassinello/claude-plugin-prd-workflow/plugin-repairgit clone --depth 1 https://github.com/Yassinello/claude-plugin-prd-workflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/yassinello/claude-plugin-prd-workflow/plugin-repair)<a href="https://agentmods.dev/commands/yassinello/claude-plugin-prd-workflow/plugin-repair"><img src="https://agentmods.dev/badge/commands/yassinello/claude-plugin-prd-workflow/plugin-repair.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00682 |
| Opus 5 | $0.00000 | $0.00341 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade B, and why
plugin-repair scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cp ~/.claude-code/plugins/claude-prd-workflow/.claude/config.json ~/config-backup.json How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Repair Command
You are helping the user repair their claude-prd-workflow plugin installation.
Your Task
Run the automatic repair tool to fix common installation issues.
Steps
-
Diagnose the problem
- First run health check to identify issues
- Show the user what's wrong
-
Attempt automatic repair
cd ~/.claude-code/plugins/claude-prd-workflow node bin/repair.js -
Verify repair
- Health check is automatically run after repair
- Show the results to the user
-
Provide next steps
- If successful: Remind user to restart Claude Code
- If failed: Provide manual repair instructions
What This Command Fixes
- Missing command files
- Missing agent files
- Missing skill files
- Corrupted plugin metadata
- Incomplete installations
Example Flow
🔧 Running repair tool for claude-prd-workflow...
📋 Step 1: Running diagnostic check...
❌ Slash commands: Directory exists but empty
✅ AI agents: 17 files found
✅ Skills: 13 files found
============================================================
🔨 Step 2: Attempting automatic repair...
🔄 Reinstalling plugin...
✅ Copied commands/
✅ Copied agents/
✅ Copied skills/
✅ Installed 17 slash commands
✅ Reinstallation complete!
============================================================
🏥 Step 3: Verifying repair...
✅ All systems operational!
💡 Important: Restart Claude Code to see the changes.
============================================================
Manual Repair (if automatic fails)
If automatic repair doesn't work, guide the user through manual steps:
-
Backup current config (if exists)
cp ~/.claude-code/plugins/claude-prd-workflow/.claude/config.json ~/config-backup.json -
Reinstall plugin
cd ~/.claude-code/plugins/claude-prd-workflow node install.js -
Restore config (if backed up)
cp ~/config-backup.json ~/.claude-code/plugins/claude-prd-workflow/.claude/config.json
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 128 lines · 0 tokens per session scan B 2e0cb986c52a
plugin-repair is a command published in the GitHub repository Yassinello/claude-plugin-prd-workflow (12 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 682 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
brooks-debt
Run a Brooks-Lint tech debt assessment.
brooks-health
Run a Brooks-Lint codebase health dashboard across all four dimensions.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.