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 Security-Phoenix-demo/security-skills-claude-code --skill production-readiness-reviewgit clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-codeWrote 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/security-phoenix-demo/security-skills-claude-code/production-readiness-review)<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/production-readiness-review"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/production-readiness-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/security-phoenix-demo/security-skills-claude-code/production-readiness-review"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/production-readiness-review.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 | $0.00242 | $0.02212 |
| Opus 5 | $0.00121 | $0.01106 |
| Sonnet 5 | $0.00048 | $0.00442 |
| Haiku 4.5 | $0.00024 | $0.00221 |
Grade A, and why
production-readiness-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 2d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production readiness review
The plan is a claim. The commit history is a claim. A passing test suite is a weaker claim than it looks. Only the code, its wiring, its configuration and its behaviour under failure are evidence. The job here is to try to disprove that the work is done and to report what survived that attempt.
Two failure modes to avoid, in order: approving something that is not finished, and producing a long review that never actually opened the files. Both come from reading the plan instead of the repo.
Phase 0 — Input contract
State what is under review before starting. Ask once, in one message, for whatever cannot be inferred, then proceed with what is available and record the rest as a scope limit.
- Repo path(s), branch or PR, and the base ref the change is measured against.
- The plan/PRD/implementation-plan artefacts and their versions.
- Target environment and how it differs from local (managed DB, secrets store, replicas).
- How to run the tests, the linter, and the type checker. If they cannot be run, say so — a review that never executed the suite is a documentation review, and must be labelled as one.
- Whether remediation is authorised now, and up to which severity.
Phase 1 — Deterministic scan
Run the bundled scanner first. It is reproducible, quotable, and diffable across runs, which the model's own reading of the tree is not.
bash ${CLAUDE_SKILL_DIR}/scripts/scan_repo.sh /path/to/repo --base origin/main > scan.md
${CLAUDE_SKILL_DIR} resolves to this skill's own directory, so the path works whether the
skill is installed personally, in a project, or as part of a plugin.
It reports: incompleteness markers, swallowed errors and silent fallbacks, debug and suppression leftovers, secret-shaped literals, route definitions vs auth markers, config and migration artefacts, test surface, and the change surface vs base.
Its output is leads, not findings. Open each hit and judge it in context; a TODO in
a comment about future work is noise, a TODO where a permission check belongs is
Critical. Also run the suite, the linter and the type checker, and record the exact
commands and results.
What ships with it
3 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.
- 2d ago First seen · 173 lines · 242 tokens per session scan A 9b4a52f23142
production-readiness-review is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (70 stars, last pushed yesterday), licensed MIT. It adds 242 tokens to every session and 2,212 once invoked, about $0.0012 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 2026-09-11.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…