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 implementgit 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/implement)<a href="https://agentmods.dev/skills/michaelycjo/specseal/implement"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/implement/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/implement"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/implement.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 | $0.00130 | $0.07369 |
| Opus 5.5 | $0.00052 | $0.02948 |
| Sonnet 5.5 | $0.00026 | $0.01474 |
| Haiku 4.5 | $0.00013 | $0.00737 |
Grade A, and why
implement 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 4d 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement — spec-driven implementation
Methodology for implementing against written specs, leaving a case behind
each rule, and closing the loop with review. Opened by the smith agent at
its first step; usable directly.
skills/agent-contract/SKILL.md binds this session too, and only if you
load it. A session driving the work directly reads this skill and never
agents/*.md, so the contract every agent it spawns receives at startup
reaches it by being opened rather than by arriving — user-invocable: false
permits the load and does not oblige it. #107's headline failure is an
orchestrator breaking a rule it had put into every prompt it sent.
If you are orchestrating a work item rather than building it, read
skills/implement/orchestration.md before the first edit; an implementer
never opens it, and everything below is the implementer's and the
orchestrator's alike.
The language the records are written in
Read Record language in config.md before writing any of the documents
below, the same way commit-pr-convention reads its own row before a commit
or a pull request. The root is resolved the way every path in this skill is.
| Item | Value |
|---|---|
| Record language | Korean |
It governs the prose in spec.md, plan.md, overview.md,
questions.md, changelog.md, the cell contents of rounds/round-N.md and
phases/phase-N.md and the text beneath their tables.
Every way of not naming one lands on English — no file, no such row, an empty value, a file that cannot be read. A config nobody can read must not stop the work.
It is independent of Commit and pull request language. Setting one does
not carry the other, and the two surfaces have different audiences: a pull
request is read by whoever opens it, and a record is read by whoever comes
back to the decision six months later.
What stays English whatever it says, because these are read literally
rather than by a person: every field name, section heading and vocabulary
word the checkers match, listed in templates/config.md under What no row
governs — that list is derived from the checkers' own constants, so it
cannot drift from them; <!-- specs/<work-item-id> --> and the other
markers; a drained line and the closed that opens a closed row; and all
code — identifiers, comments, docstrings, file names, test function names. A
translated field name is not a translation, it is a checker that
stops reading.
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.
- 4d ago Changed · -16 lines e07b41aaaa91
- 7d ago Changed · +48 lines 38934f98bdfb
- 12d ago Changed · -59 lines dbff9bdf37f2
- 14d ago Changed · -96 lines · +2 tokens per session 2fc820e7e74f
- 17d ago Changed · +5 lines bb648fad4188
- 24d ago Changed 023b9e1302f1
- 25d ago Changed · +5 lines cbe2e71fa8df
- 26d ago Changed · +5 lines 78ec508dbc29
- 27d ago Changed · +15 lines e8f5e7ac30af
- 1mo ago First seen · 605 lines · 128 tokens per session scan A 01bfe9428c9f
implement is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 130 tokens to every session and 7,369 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…