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 gap-analysisgit 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/gap-analysis)<a href="https://agentmods.dev/skills/michaelycjo/specseal/gap-analysis"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/gap-analysis/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/gap-analysis"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/gap-analysis.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 | $0.00105 | $0.01236 |
| Opus 5.5 | $0.00042 | $0.00494 |
| Sonnet 5.5 | $0.00021 | $0.00247 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
gap-analysis 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gap-analysis, how far the build drifted from the document
A design document and the code it produced diverge in three directions, and only one of them is obvious. Missing is easy to see. Extra, built but never specified, and divergent, built to a different rule than written, are what this looks for.
Comparison dimensions
Four kinds, whatever the project is. The examples name a web service because that is the common case, not because it is the only one; substitute the equivalent and the dimension still holds.
-
The surface others touch: whatever a caller reaches for, and what comes back. HTTP paths, methods and status codes; a CLI's flags, exit codes and stdout shape; a library's exported names and signatures; a screen's controls and states; a queue's topics and message shapes.
-
The shape of what persists: entities and relationships, field names, types and constraints, and how existing data gets to the new shape. Tables and migrations; a file format and its version field; cache keys and their expiry; what a client keeps on disk between launches.
-
The rules that decide: feature completeness, edge cases, error scenarios, validation. This dimension is the same everywhere and is usually where the real divergence hides, because it is the one a document describes in prose rather than in a table.
-
Conventions: naming, folder structure, import patterns, error message format. Drift here is rarely a defect on its own; it is the signal that the document stopped being read partway through.
If a dimension does not apply (a pure library persists nothing), say so and move on. Recording it as a match claims a walk nobody made; leaving it out silently makes a partial walk look complete.
Verdicts
Per item, one of four:
- Match: implemented as designed.
- Partial: implemented differently; say how.
- Missing: not implemented.
- Extra: implemented, not in this document. That is not the same as unspecified: a repository accumulates specifications, and the second one routinely authorises what the first never mentioned. Say where else the walk looked before calling it unspecified.
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 tokens per session 0af597db0d2c
- 14d ago Changed · +5 tokens per session 89cc2f3e3b03
- 2mo ago First seen · 127 lines · 101 tokens per session scan A fc1bed628eb4
gap-analysis is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 105 tokens to every session and 1,236 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 2026-08-31.
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…