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/juanmhidalgo/claude-plugins/fixes-plangit clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote 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/juanmhidalgo/claude-plugins/fixes-plan)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/fixes-plan"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/fixes-plan.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 5.1 | $0.00035 | $0.00712 |
| Opus 5 | $0.00017 | $0.00356 |
| Sonnet 5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
fixes-plan scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Branch: !
git branch --show-current - Date: !
date +%Y-%m-%d - Feature name: $ARGUMENTS
Existing Files Check
Check for existing review-fixes files before creating a new one:
- Look for
REVIEW_FIXES.mdin the repo root - Look for
docs/review-fixes-*.mdfiles - Look for files with
type: review-fixesin their frontmatter
Instructions
Step 1: Check for Existing File
Look for files with type: review-fixes in frontmatter, or REVIEW_FIXES.md.
If an existing fixes file is found:
- Read the existing file
- Ask user: "Found existing
[filename]. Do you want to:"- Update - Add new issues, preserve existing ones and their status
- Replace - Generate fresh document
- New file - Create separate file
If updating:
- Keep all existing issues and their completion status
- Add new issues from recent reviews
- Update the Progress Summary table
- Update
updatedfield in frontmatter
Step 2: Gather Issues
Sources for new issues:
- Recent
/code-review/branchoutput in this conversation - Recent
/code-review/triageoutput (verified issues only) - Any issues mentioned by the user
For Each Issue
-
Classify priority:
- CRITICAL: Security, data loss, blocking bugs, migrations
- HIGH: N+1 queries, race conditions, missing validation
- MEDIUM: Inconsistencies, deprecated APIs, missing indexes
- LOW: Style, docs, refactoring
-
Document clearly:
- Descriptive title
- File path with line numbers
- Clear problem statement
- Solution with code example
- Empty notes section for implementation
-
Provide actionable solutions:
- Include actual code, not just description
- Consider edge cases
- Note if solution requires migration
Output
- Generate the markdown document following the template
- Ask user where to save:
docs/review-fixes-{branch}.mdREVIEW_FIXES.mdin project root- Custom path
- Write the file to the chosen location
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 · 104 lines · 35 tokens per session scan A 3005be1e5543
fixes-plan is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 712 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.