Borrowing it
Nothing to install: this file belongs to w00fx/spec-anchored-agentic-development. 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/w00fx/spec-anchored-agentic-development/main/.agents/skills/review-spec-drift/SKILL.mdgit clone --depth 1 https://github.com/w00fx/spec-anchored-agentic-developmentWrote 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/w00fx/spec-anchored-agentic-development/review-spec-drift)<a href="https://agentmods.dev/skills/w00fx/spec-anchored-agentic-development/review-spec-drift"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/review-spec-drift/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/w00fx/spec-anchored-agentic-development/review-spec-drift"><img src="https://agentmods.dev/badge/skills/w00fx/spec-anchored-agentic-development/review-spec-drift.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 | $0.00011 | $0.00199 |
| Opus 5 | $0.00005 | $0.00100 |
| Sonnet 5 | $0.00002 | $0.00040 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
review-spec-drift 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.
What it actually says
For the capability in the argument (or the current one if omitted):
- Read the spec in specs//.
- Read the contracts in specs//contracts/.
- Read the corresponding implementation code.
- Identify discrepancies:
- Behaviors described in the spec not implemented
- Behaviors in the code not anticipated in the spec
- Schemas in contracts that don't match the code
- Report in the format:
- Critical drift (blocks production)
- Relevant drift (fix next sprint)
- Cosmetic drift (update spec)
Don't fix anything. Just report.
Portability: this skill's body works as a standalone prompt in any harness — the semantic procedure is portable; invocation, permissions, and context loading need the harness adapter.
What ships with it
1 file 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.
- 5d ago First seen · 24 lines · 11 tokens per session scan A f6ceaaa0d78e
review-spec-drift is a skill published in the GitHub repository w00fx/spec-anchored-agentic-development (5 stars, last pushed 7d ago), licensed MIT. It adds 11 tokens to every session and 199 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
A3 — Polish
Code/content quality. Dead code, hardcoded values, leftover TODOs, weak error handling, security holes, performance traps, standards violations. Enforces the Double Gate — blocks until A1 is at zero findings.
A1 — Design & Master-Spec Consistency
The drift check. Compare what was built against the design doc and master spec. Sets the Double Gate — A3 cannot start until A1 is at zero findings.
Final — The F-Pass
The feature-wide final audit. Re-runs the five lenses across ALL groups together, then two extra passes — Dreamland (dream perfection, then make it real) and Simulation (realistic scale testing). Runs after every group is accepted.
A2 — Spec Review
Mechanical FR/AC compliance. Walk every functional requirement and acceptance criterion and render a binary Pass/Fail with evidence. No judgment about quality, direction, or architecture.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
spec-kitty-mission-review
Review a fully merged Spec Kitty mission post-merge (all WPs done/approved) to verify spec→code fidelity, FR coverage, drift, risks, and security. Triggers: "review the merged mission", "post-merge mission review", "verify the completed mission", "audit the mission implementation", "mission-level acceptance review"…