Borrowing it
Nothing to install: this file belongs to lbruton/claude-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lbruton/claude-context/master/.agents/skills/spec-review/SKILL.mdgit clone --depth 1 https://github.com/lbruton/claude-contextWrote 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/lbruton/claude-context/spec-review)<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-review"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/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/lbruton/claude-context/spec-review"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/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 | $0.00022 | $0.02014 |
| Opus 5.5 | $0.00009 | $0.00806 |
| Sonnet 5.5 | $0.00004 | $0.00403 |
| Haiku 4.5 | $0.00002 | $0.00201 |
Grade A, and why
spec-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-review
Vault paths (DEVS-78): resolve once per session with
vault-path(~/.local/bin/vault-path).PROJECT_VAULT=$(vault-path project)is<repo>/DocVault/, and edits ride the current branch and PR.SHARED_VAULT=$(vault-path shared)is usually/Volumes/DATA/GitHub/Devops/DocVault/, and edits commit directly to Devopsmain(DocVault/**only). Sensitive pages from public repos go in$(vault-path private).
You are the peer reviewer for a single phase of an active /spec. This is the reviewer-side skill; the originating agent invoked /spec review <ISSUE-ID> <phase> <your-name> and handed you a pointer to this skill instead of pasting a long prompt.
Invocation
/spec-review <ISSUE-ID> <phase> [REVIEWER-TAG]
<ISSUE-ID>— the issue prefix and number, e.g.STRK-123,STAK-457.<phase>— one ofrequirements,discovery,approach,tasks.[REVIEWER-TAG]— optional. The uppercase tag used to prefix your comments (e.g.OPUS,GEMINI,DEEPSEEK,KIMI,CODEX). If omitted, you will be prompted.
If ISSUE-ID or phase is missing, print:
Usage: /spec-review <ISSUE-ID> <phase> [REVIEWER-TAG]
phase ∈ requirements | discovery | approach | tasks
REVIEWER-TAG — uppercase label for your review blocks (e.g. OPUS, GEMINI, KIMI)
…and exit. Do not guess.
Hard gates (run in order; fail fast)
- Resolve the spec directory. It lives at
{specs-root}/{ISSUE-ID}-{slug}/, in-repo (the worktree's copy when run from a worktree). Resolve{specs-root}per.agents/skills/spec/references/conventions.md→ Folder resolution (specs.pathin.claude/project.json, defaultDocVault/specs). Glob for{specs-root}/{ISSUE-ID}-*(ignorearchive/) — there should be exactly one match. If zero or multiple, STOP and print the candidates. - Locate the target file.
{SPEC_DIR}/{phase}.md. If absent, STOP: "Phase{phase}has not been drafted yet for {ISSUE-ID}." Read the phase files it depends on too (discovery → requirements; approach → requirements + discovery; tasks → all four), plusAGENTS.mdand.context/GLOSSARY.mdif present. - Establish your reviewer tag (
{{COMMENT_PREFIX}}). Do NOT auto-detect or guess based on model name — models misidentify themselves across harnesses.- If a
REVIEWER-TAGargument was supplied on invocation, use it as-is (uppercase). - Otherwise, ask the user: "What tag should I use for this review? (e.g. OPUS, GEMINI, DEEPSEEK, KIMI, CODEX)" — wait for their answer before continuing.
- This tag appears in every
> {{COMMENT_PREFIX}}:comment and the## {{COMMENT_PREFIX}} Reviewsection header.
- If a
- Detect existing peer reviews without blocking new reviewers. Scan the target file for inline
> {prefix}:blocks or## {prefix} Reviewsections NOT nested under## Review Archive.- If unreconciled review from other reviewers is present, keep going. Preserve those comments exactly and add your own
{{COMMENT_PREFIX}}comments alongside them. Multiple peer reviewers are expected to update the same phase file before reconciliation. - If unreconciled review from your own
{{COMMENT_PREFIX}}is already present, STOP: "Review from {{COMMENT_PREFIX}} is already present in {phase}. Ask the human whether to rerun this reviewer or reconcile first." - Do not tell the human to run
/spec reconcilejust because OPUS, DEEPSEEK, GEMINI, KIMI, CODEX, or another peer reviewer has already left comments. Reconciliation happens once, after all requested peer reviews have updated the file.
- If unreconciled review from other reviewers is present, keep going. Preserve those comments exactly and add your own
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.
- 5d ago Changed a1306ef8c4b9
- 9d ago Changed 72ae9d885e1b
- 11d ago First seen · 119 lines · 22 tokens per session scan A 8c9e9123570e
spec-review is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 2,014 once invoked, about $0.0001 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 2026-10-17.
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"…
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…
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…