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 skills add cmdr-chara/codex-toolkit --skill review-and-refactor-codegit clone --depth 1 https://github.com/cmdr-chara/codex-toolkitWrote 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/skills/cmdr-chara/codex-toolkit/review-and-refactor-code)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/review-and-refactor-code"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/review-and-refactor-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/review-and-refactor-code"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/review-and-refactor-code.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00038 | $0.00605 |
| Opus 5.5 | $0.00015 | $0.00242 |
| Sonnet 5.5 | $0.00008 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
review-and-refactor-code 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 24d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review and Refactor Code
Find evidence-backed problems in a defined scope and improve structure without smuggling in behavior changes.
Trigger boundary
Use this skill for a PR/diff review, a bounded maintainability assessment, cleanup, decomposition, or behavior-preserving refactor.
Do not trigger for broad repository discovery, an unknown runtime cause, proactive bug hunting, migrations, security-only review, measured performance work, or final release approval.
Required inputs
Resolve repository/scope, base/head or bounded area, intended behavior, public/internal contracts, relevant tests, generated/vendor boundaries, constraints, approval state, and protected user work.
Safety baseline
- Preserve the working tree and uncommitted work.
- Start read-only for review/refactor assessment.
- Findings require an observable failure mode or concrete maintenance risk, not style preference.
- Do not mix feature behavior into a refactor unless explicitly requested.
- Broad edits stop at a concrete proposal unless already authorized.
Workflow
- Map the change surface. Trace changed files, callers/callees, contracts, configuration, data shape, side effects, and relevant tests.
- Admit findings. Use
references/finding-contract.md. Separate correctness/integration findings from optional structural improvements. - Define parity. Before refactoring, state behavior that must remain stable using
references/behavior-parity.md. - Characterize legacy behavior when needed. If important untested code must change, read
references/characterization-testing.mdand pin observed behavior before structural edits. - Propose the smallest useful slice. State files, invariants, expected complexity reduction, risks, and focused verification. Stop at
AWAITING_APPROVALif broad changes were not authorized. - Refactor incrementally. Keep interfaces explicit, preserve compatibility, avoid speculative abstraction, and remove old paths only after replacements are wired.
- Verify the final slice. Run targeted parity/correctness checks and inspect the final diff for accidental behavior changes.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago Changed · -136 lines · -59 tokens per session 252ace6eff26
- 1mo ago First seen · 185 lines · 97 tokens per session scan A 95ae1907b4fb
review-and-refactor-code is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 38 tokens to every session and 605 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.