Borrowing it
Nothing to install: this file belongs to WolframResearch/AgentTools. 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/WolframResearch/AgentTools/main/.claude/skills/review-spec/SKILL.mdgit clone --depth 1 https://github.com/WolframResearch/AgentToolsWrote 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/wolframresearch/agenttools/review-spec)<a href="https://agentmods.dev/skills/wolframresearch/agenttools/review-spec"><img src="https://agentmods.dev/badge/skills/wolframresearch/agenttools/review-spec/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/wolframresearch/agenttools/review-spec"><img src="https://agentmods.dev/badge/skills/wolframresearch/agenttools/review-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.00995 |
| Opus 5.5 | $0.00037 | $0.00398 |
| Sonnet 5.5 | $0.00018 | $0.00199 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
review-spec 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a Design Specification
Review a design specification against the actual codebase to surface inaccuracies, missing details, convention violations, and potential issues — before implementation begins. The goal is to catch problems that would cause confusion or rework during implementation.
Spec to review: $ARGUMENTS
If no specific spec is given, ask the user which spec in Specs/ they'd like reviewed.
Process
1. Read the Spec
Read the full spec file. As you read, collect:
- Referenced files: Every source file mentioned (implementation touchpoints, code examples, "see also" references)
- Factual claims: Specific assertions about existing code (option names/defaults, function signatures, symbol locations, data structures, file paths)
- New additions: Symbols, options, files, or behaviors the spec proposes to add
- Behavioral descriptions: How existing functions work, what they accept, what they return
2. Cross-Reference with the Codebase
Read all referenced files in parallel using the Explore agent or direct reads. For each file, verify:
- Options and signatures: Do the current options match what the spec claims? Are default values correct? Does the spec list all required changes?
- Symbol locations: Are symbols declared where the spec says they should be (e.g., CommonSymbols.wl vs private context)? Follow existing conventions — if similar symbols are private in other files, new ones should be too.
- Function behavior: Does the code actually work the way the spec describes? Look at the actual implementation, not just the signature.
- Naming and conventions: Do proposed names follow codebase conventions (lowerCamelCase for internal functions, UpperCamelCase for exported, etc.)?
- Implementation touchpoints completeness: Are there files that would need changes but aren't listed? For example, if a new path variable is added, does it need a declaration in CommonSymbols.wl AND a definition in Files.wl?
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 · 90 lines · 92 tokens per session scan A c678ead8d9c9
review-spec is a skill published in the GitHub repository WolframResearch/AgentTools (96 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 995 once invoked, about $0.0004 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 2026-08-30.
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…