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 MichaelYcJo/SpecSeal --skill code-reviewgit clone --depth 1 https://github.com/MichaelYcJo/SpecSealWrote 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/michaelycjo/specseal/code-review)<a href="https://agentmods.dev/skills/michaelycjo/specseal/code-review"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/code-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/michaelycjo/specseal/code-review"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/code-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 | $0.00113 | $0.02167 |
| Opus 5.5 | $0.00045 | $0.00867 |
| Sonnet 5.5 | $0.00023 | $0.00433 |
| Haiku 4.5 | $0.00011 | $0.00217 |
Grade A, and why
code-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 7d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review — spec first, then quality
Assume the code has defects, and look for them. A pass with no grounds is
forbidden: where you are unsure, write a question, not a pass. A session
orchestrating a review run reads skills/code-review/orchestration.md before
round 1.
Two stages, in order
- Spec compliance: the code against the written spec, the
docs/policies first and then the work item's SDD set underseal/specs/. Look for behaviour that is missing and for behaviour nobody asked for. Read the code, not the implementer's report of it. - Quality, only after stage 1: correctness, error handling, security, performance, test quality.
The work item's overview.md arrives in the diff and is the implementer's
account, so stage 1 governs it. Its divergences, its ## Not verified rows
and the clauses it fed back into the spec are claims to check, and an
account citing a clause it added is citing itself. Settle what you can; what
only a person can answer stays a question. Do not edit it.
Review beyond the changed files: new code that calls into untouched files puts their conditions and boundaries into effect for the first time, so follow every call the change introduces. check: evals/behaviour/warden/rule-warden-one-finding/
Comparison axes
Fix the axes before starting and cover all of them.
| Axis | Compare |
|---|---|
| Inputs | names, types, required/optional, defaults, accepted ranges |
| Authorization | who acts/queries as whom; self/admin/other branches |
| Query scope | which set is targeted: period, ownership, status filters |
| Exclusions & boundaries | excluded states, overlap conditions, boundary values (rarely written down — most frequent divergence point) |
| Deliberate non-exclusions | what the spec intentionally does not filter; new code tends to "clean it up" |
| Ordering, dedup, response shape | sort keys, tie-breaking, dedup basis, included/excluded fields |
| Error paths | failure conditions, codes, messages; failure vs. empty result. Count new failure paths the change introduces separately — someone must classify each as fix or regression |
| State transitions | against the spec's state machine, if one exists |
| Concurrency & atomicity | what can change between the read that decides and the write that acts: state held across an external call or await, transaction boundary against lock scope, whether a retry executes twice |
| Security | who can reach this path and as whom; the trust of every input that crosses an OS or process boundary; whether each failure fails open or closed; what a crafted name, path, or payload reaches |
What ships with it
2 files 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.
- 7d ago Changed · +1 lines 1df6125b6022
- 11d ago Changed · +7 lines acadc5f7a1d9
- 12d ago Changed · -146 lines fb6716469f82
- 14d ago Changed · -158 lines d67fb2d21881
- 17d ago Changed · +3 lines 5c1c7ebaa781
- 1mo ago Changed · +1 lines ed7a626d01d9
- 1mo ago Changed · +1 lines 7c3a7cb6e4ce
- 1mo ago Changed · +24 lines f9487c28a14e
- 1mo ago Changed · +34 lines 89be9e7d2fa9
- 1mo ago First seen · 399 lines · 113 tokens per session scan A d7d858e031a8
code-review is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 2,167 once invoked, about $0.0005 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
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
pr-review
Use when the user wants to deeply review a pull/merge request or a local diff — "review this PR", "grill the MR", "stress-test this diff", "deep-dive code review", "code review before merge", or when they name a PR/MR URL, number, branch, commit range (A..B/A...B), tag or SHA. Works on GitHub (gh), GitLab (glab), or a…
genshijin-review
A compact pull-request review format that writes one actionable finding per line in Japanese or English.
skill-distiller
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to "distill skills for X", "find and combine skills for X", "synthesize skills", "merge skills", "make a skill for X from skills.sh", "update distilled skill", or…