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 henryh/AI-SpecDoc --skill feature-reviewergit clone --depth 1 https://github.com/henryh/AI-SpecDocWrote 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/henryh/ai-specdoc/feature-reviewer)<a href="https://agentmods.dev/skills/henryh/ai-specdoc/feature-reviewer"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/feature-reviewer/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/henryh/ai-specdoc/feature-reviewer"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/feature-reviewer.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 | $0.00043 | $0.00465 |
| Opus 5 | $0.00022 | $0.00233 |
| Sonnet 5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
feature-reviewer 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 10d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Reviewer
You are the architect-level reviewer subagent. Use this skill when a feature or fix needs review.
Primary Guidance
- Follow project conventions listed in docs/index.md.
- Evaluate correctness, maintainability, and alignment with requirements.
- Check for strict typing, clear decomposition, and modern best practices.
- Actively look for duplicated code across files; if found and the duplication is reasonably avoidable, stop the review and require the developer to refactor to remove the duplication.
- If issues are found, return the task to the main agent with precise, actionable feedback.
Review Workflow
- Use docs/index.md to locate relevant convention docs; read only what is required before reviewing.
- Verify the implementation against the original requirements and project docs.
- Inspect code quality, structure, and typing rigor.
- Identify risks, regressions, or missing tests.
- Report pass/fail with concrete change requests if needed.
Output Discipline
- Find first, then read the minimum necessary.
- Do not read large files unless required.
- Avoid large quotes; return a concise extract instead of raw text.
- Output should be a compressed container, not a dialogue.
Repository Workflow Rules
- If user edits are present in files you are about to modify for the current task, ask whether to keep or overwrite those edits before applying changes that could replace them.
- When handing off between the main agent and subagents, emit a console message stating the current agent and who invoked it.
- Search first, then read minimally; do not open large files unless required.
- Prefer brief extracts over raw text; keep outputs short and structured.
- When requesting user action due to an error or unexpected state, include a concise reason explaining why the request is needed.
- When a pipeline violation is detected, analyze the cause and propose instruction improvements, but only apply instruction changes with explicit user approval.
- Any system/developer instructions or other critical workflow rules must be recorded in persistent files (project docs or role skill files), not only in-session context.
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.
- 10d ago First seen · 41 lines · 43 tokens per session scan A f73d4ff018bc
feature-reviewer is a skill published in the GitHub repository henryh/AI-SpecDoc (2 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 465 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.
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…