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 commit-pr-conventiongit 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/commit-pr-convention)<a href="https://agentmods.dev/skills/michaelycjo/specseal/commit-pr-convention"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/commit-pr-convention/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/commit-pr-convention"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/commit-pr-convention.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 | $0.00109 | $0.02799 |
| Opus 5.5 | $0.00044 | $0.01120 |
| Sonnet 5.5 | $0.00022 | $0.00560 |
| Haiku 4.5 | $0.00011 | $0.00280 |
Grade A, and why
commit-pr-convention 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commit-pr-convention, the format of commits, pull requests and branches
This skill is read by whoever writes a commit, a pull request or a branch
name: the smith, and the orchestrator, which also writes the code where
routing.md answers Implementation with the session. Below, that party
is the writer.
writing-style governs what a pull request body says and how it is
built. This skill governs the envelope: the prefix, the title's shape, the
branch name, and where a translation lives. A body can satisfy one and
violate the other.
First, check the title against the history
gh pr list --state all --limit 10
The history is the rule even where no document states it. Everything below was read off a repository's log, and repositories differ. A title that does not look like the ones in that list is the one that is wrong.
This step is first because the failure happens here: a list on screen is not a comparison made. Having run the command is not the same act as comparing the title to what it returned, so the writer makes the comparison in one line before opening anything.
An empty list is an answer, not a blocker. A repository with no pull requests yet has no history to outrank anything, so the table in the next section is what the writer uses, unchanged, and the first title written becomes the history the next one is compared against.
The language is the repository's, and it says so in a file
The writer reads config.md in the root before writing any of the five
things below. The root is <repo>/seal/ where that directory exists and
$(git rev-parse --git-common-dir)/seal/ otherwise, which is where local
mode keeps it; resolve it that way rather than spelling the first place and
stopping.
| Item | Value |
|---|---|
| Commit and pull request language | Korean |
That row governs the commit subject and body, the pull request title and body (all four, because a squash makes them one text) and the review report posted as a pull-request comment, which is prose for whoever opens that pull request.
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 · +20 lines 3501f5af6abc
- 7d ago Changed · +2 lines 558354c56680
- 14d ago Changed d44ec0cf649b
- 1mo ago Changed · +13 lines 6c38ed6089e4
- 1mo ago First seen · 217 lines · 109 tokens per session scan A 0dd8d7303b09
commit-pr-convention is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 109 tokens to every session and 2,799 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 2026-09-04.
Other skills, from other repositories
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…
pr-review
Review pull requests and Git diffs with Graph-It-Live risk, breaking-change, dependency-impact, cycle, unused-export, and test-candidate evidence. Use when asked to review a PR, inspect a diff, assess merge risk, check a branch before merging, create a Graph-It-Live review gate, or explain review-pr results. Trigger…
review-loop
Have a second model review a branch on this machine before its pull request opens, fix what holds up, and repeat until a round comes back clean or three rounds pass. Use when about to open a pull request or push a fix to one, when the user says review loop or asks for a second opinion before the PR, or when a repo's…
loop-gh-pr
A recipe for a scheduled GitHub pull-request watcher. It checks open pull requests for new activity and prepares read-only review drafts without posting comments or merging anything.