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 skills/nwiizo/ccswarm/review-fixnpx skills add nwiizo/ccswarm --skill review-fixgit clone --depth 1 https://github.com/nwiizo/ccswarmWhat 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 | $0.00020 | $0.00569 |
| Opus 5 | $0.00010 | $0.00284 |
| Sonnet 5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
review-fix 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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When subagents are enabled in Codex, prefer delegating this workflow to the review-fix-agent custom agent.
Review uncommitted changes, fix actionable issues, and verify the result.
Workflow
Phase 1: Scope
git status --shortandgit diff --stat HEADto determine what changed.- If no changes exist, abort with "nothing to review".
Phase 2: Baseline
Run build and lint to establish a clean starting point:
cargo clippy --workspace -- -D warnings 2>&1 | tail -20
cargo test --workspace --no-run 2>&1 | tail -5
If the baseline already fails, report the failures and stop. Do not mask pre-existing breakage.
Phase 3: Review
Inspect the diff and new untracked files. Check for:
| Category | What to look for |
|---|---|
| Stale references | Deleted modules, commands, docs, or templates still referenced |
| Code duplication | Identical structs or functions across files worth extracting |
| Provider abstraction gaps | Hard-coded CLI names instead of the AgentProvider trait |
| Dead async | Async work discarded and then repeated synchronously |
| Sort instability | Utc::now() used as a fallback sort key |
| Hardcoded paths | Filesystem paths that should be relative to repo_path |
| Unused params | Accepted CLI arguments silently ignored |
| Security | Path traversal, credential leaks, unchecked user input |
Classify each finding:
- Fix: clear bug or correctness issue. Fix it now.
- Warn: design concern or missing feature. Report it, but do not fix unless trivial.
- Note: style or informational only.
Phase 4: Fix
For each fix-level finding:
- Make the minimal, surgical edit.
- Do not change unrelated code.
- After all fixes, run:
cargo clippy --workspace -- -D warnings
cargo test --workspace --no-run
If clippy or test compilation fails, revert the offending edit and downgrade it to a warning.
Phase 5: Report
Output a structured summary:
## Review + Fix Report
### Fixed
- <file>:<line> - <description>
### Warnings
- <file>:<line> - <description>
### Notes
- <description>
### Verification
- clippy: PASS / FAIL
- test compile: PASS / FAIL
- files modified: N
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.
- yesterday First seen · 88 lines · 20 tokens per session scan A dddf0190ba4c
review-fix is a skill published in the GitHub repository nwiizo/ccswarm (149 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 569 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…