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 adamdaw/claude-code-skills --skill spec-reviewgit clone --depth 1 https://github.com/adamdaw/claude-code-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/adamdaw/claude-code-skills/spec-review)<a href="https://agentmods.dev/skills/adamdaw/claude-code-skills/spec-review"><img src="https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/spec-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/adamdaw/claude-code-skills/spec-review"><img src="https://agentmods.dev/badge/skills/adamdaw/claude-code-skills/spec-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 | $0.00085 | $0.02313 |
| Opus 5.5 | $0.00034 | $0.00925 |
| Sonnet 5.5 | $0.00017 | $0.00463 |
| Haiku 4.5 | $0.00009 | $0.00231 |
Grade A, and why
spec-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 1mo 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec review (Gate 1)
Runs one cold pass over a GitHub work-item issue treated as the Software Design Document. The reviewer is a fresh subagent invocation; it reads the published issue body and reports findings. Nothing is built.
Throughout, the Architect means the human who owns the spec and declares the gate green.
Why a subagent and not this session
The session that authored the spec cannot review it. A fresh invocation is the structural independence reset — a fresh window resets memory, but a separate invocation is what establishes production independence. Never review a spec you wrote in the same context.
Inputs the reviewer gets, and nothing else
- The issue number and the repo (
owner/name). - The tracker ticket ID, so it can read the SRS. This gate checks that the SDD faithfully encodes the SRS, so withholding the SRS makes that uncheckable — and invites the reviewer to demand a Requirements section the house SDD skeleton deliberately does not have. The SRS is a source artifact, not deliberation.
- The path to
CONSTITUTION.mdin the local checkout. If that checkout is a stale mirror, tell the reviewer to read it fromorigin/maininstead. - The prompt below, verbatim.
It fetches both bodies itself. Do not paste them in, do not summarise them, and do not mention what you think is wrong with either.
Never pass prior-pass findings, your own reasoning, or the ticket's internal rationale. Those are the deliberation record. Feeding any of them back means the pass returns your own conclusions instead of an independent read.
Where the record lives
Keep two files per ticket, wherever your team keeps its work-item records:
work-item.md— the spec body. The authoring surface.spec-review.md— every pass appended under a## Pass Nheading, with the disposition written under each finding.
Edit work-item.md, then push it. Never edit the issue body on GitHub
directly. One direction only is what keeps the two from drifting.
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.
- 1mo ago First seen · 212 lines · 85 tokens per session scan A 78889beec1e1
spec-review is a skill published in the GitHub repository adamdaw/claude-code-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 85 tokens to every session and 2,313 once invoked, about $0.0003 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…