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 parity-setupgit 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/parity-setup)<a href="https://agentmods.dev/skills/michaelycjo/specseal/parity-setup"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/parity-setup/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/parity-setup"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/parity-setup.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 | $0.00031 | $0.00777 |
| Opus 5.5 | $0.00012 | $0.00311 |
| Sonnet 5.5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
parity-setup 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specseal:parity-setup, turn on parity mode
The user runs this command, and the session running it writes
seal/parity.md, whose presence is the declaration that this repository ports
behavior from another codebase. That turns on the three-way judgment between
policy, the original and the new code, with the original preserved where the
policy is silent, and lets the scribe agent fetch what the original does.
The implement skill's bootstrap asks this question once, when it first sets
a repository up. This command is for when the answer was no at the time, when
the layout predates the question, or when the original repository changes.
Procedure
-
Stop if it already exists. If
seal/parity.mdis present, show it and ask what should change instead of overwriting a declaration someone made. -
Find candidates for the original. Do not ask the user to type a path from memory when the machine can propose one:
- sibling directories of this repository that are git checkouts, because a port usually sits beside its original;
- an upstream or fork relation in
git remote -v; - repositories whose directory structure overlaps this one's.
Present what was found with what each one is, and let the user pick or give a path. Never guess. A comparison against a guessed original proves nothing, which is worse than having no parity mode at all.
-
Read the baseline.
git -C <original> rev-parse HEAD. This is the commit the original's coordinates will refer to, so record the SHA and the date it was read. -
Confirm the module. A port often covers one directory of a larger original (
apps/foo), not the whole repository. Ask where the original has an obvious multi-module layout. -
Policy root. Read it from the tree: the directory where this repository already keeps ratified policy, such as
docs/, ornonewhere it keeps none. Never propose creating one. -
Write two files.
seal/parity.mdfromtemplates/parity.md, committed. Coordinate-trust exceptions start empty.~/.claude/specseal/parity-paths.md: the machine-local checkout path, keyed by this repository's origin remote URL so worktrees and second checkouts resolve to one entry. This never goes in the committed file: it is wrong for every other machine.
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 · -10 lines 2b4b438fff87
- 7d ago Changed · +4 lines · +1 tokens per session e280f5ea844d
- 11d ago Changed · +1 lines c0997c6e5419
- 14d ago Changed 17657be1e5a5
- 1mo ago Changed · -2 tokens per session 3a605cac103b
- 2mo ago First seen · 74 lines · 32 tokens per session scan A 5716be2873fc
parity-setup is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 777 once invoked, about $0.0001 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…