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 BenedictKing/benedictking-skills --skill codex-reviewgit clone --depth 1 https://github.com/BenedictKing/benedictking-skillsWrote 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/benedictking/benedictking-skills/codex-review)<a href="https://agentmods.dev/skills/benedictking/benedictking-skills/codex-review"><img src="https://agentmods.dev/badge/skills/benedictking/benedictking-skills/codex-review/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/benedictking/benedictking-skills/codex-review"><img src="https://agentmods.dev/badge/skills/benedictking/benedictking-skills/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 100 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 435 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 354 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00044 | $0.05930 |
| Opus 5 | $0.00022 | $0.02965 |
| Sonnet 5 | $0.00009 | $0.01186 |
| Haiku 4.5 | $0.00004 | $0.00593 |
Grade A, and why
codex-review 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 9d 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 — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Code Review Skill
Trigger Conditions
Triggered when user input contains:
- "代码审核", "代码审查", "审查代码", "审核代码"
- "review", "code review", "review code", "codex 审核"
- "帮我审核", "检查代码", "审一下", "看看代码"
Core Concept: Intention vs Implementation
Running codex review --uncommitted alone only shows AI "what was done (Implementation)".
Recording intention first tells AI "what you wanted to do (Intention)".
"Code changes + intention description" as combined input is the most effective way to improve AI code review quality.
Skill Architecture
This skill operates in two phases:
- Preparation Phase (current context): Check working directory, update CHANGELOG
- Review Phase (isolated context): Invoke Task tool to execute Lint + codex review (using context: fork to reduce context waste)
Execution Steps
0. [First] Check Working Directory Status
git diff --name-only && git status --short
Decide review mode based on output:
- Has uncommitted changes → Continue with steps 1-4 (normal flow)
- Clean working directory → Assess
HEADwith the same difficulty criteria, then invokecodex review --commit HEADwith the matching model configuration
1. [Mandatory] Check if CHANGELOG is Updated
Before any review, must check if CHANGELOG.md contains description of current changes.
# Check if CHANGELOG.md is in uncommitted changes
git diff --name-only | grep -E "(CHANGELOG|changelog)"
If CHANGELOG is not updated, you must automatically perform the following (don't ask user to do it manually):
- Analyze changes: Run
git diff --statandgit diffto get complete changes - Auto-generate CHANGELOG entry: Generate compliant entry based on code changes
- Write to CHANGELOG.md: Use Edit tool to insert entry at top of
[Unreleased]section - Continue review flow: Immediately proceed to next steps after CHANGELOG update
Auto-generated CHANGELOG entry format:
## [Unreleased]
### Added / Changed / Fixed
- Feature description: what problem was solved or what functionality was implemented
- Affected files: main modified files/modules
What ships with it
2 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.
- 9d ago First seen · 459 lines · 44 tokens per session scan A bb4a176138eb
codex-review is a skill published in the GitHub repository BenedictKing/benedictking-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 5,930 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 2026-08-30.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
audit
Audits recent work against its Definition of Done and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. Generates an incremental prompt pack for any gaps found. With…
phoenix-review
Review completed work against the Intent Contract's acceptance criteria using objective evidence, not opinion — re-run every check, confirm no regressions, inspect the tamper-evident trace, and surface only real issues (bugs, unmet criteria, regressions). Use before shipping, after a feature is built, or when the user…
pr-classify
A pull-request review process that classifies findings as Critical, Important, or Optional. A pull request is a proposed code change submitted for review before it is merged into the project.
pr-recheck
Second-pass re-review of a PR that already has review comments. Re-reads the diff and new commits against the existing open threads, marks each as addressed / partial / not addressed, resolves the addressed ones, and then either approves (only when everything is clean) or drafts new inline comments. Use when the user…
debt-ledger
Collect the deliberate-simplicity tradeoff annotations left in the code (// TRADEOFF(ceiling: ...; upgrade: ...): ...) across the repo into a single ledger — location, ceiling, upgrade path, note. Use for "debt ledger", "list tradeoffs", "what shortcuts did we take", "debt-ledger". Pairs with the TRADEOFF convention…