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 legacy-paritygit 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/legacy-parity)<a href="https://agentmods.dev/skills/michaelycjo/specseal/legacy-parity"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/legacy-parity/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/legacy-parity"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/legacy-parity.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 | $0.00085 | $0.01233 |
| Opus 5.5 | $0.00034 | $0.00493 |
| Sonnet 5.5 | $0.00017 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
legacy-parity 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
legacy-parity, the original is the fallback spec
Extends implement and code-review when the work is a migration, the same
behavior rebuilt on different technology, in a repository that declares
seal/parity.md. A scribe reads the sections that find and trace the
original: The migration config, What the original sends and The
original's coordinates. The sections that judge and record are its caller's.
Premise
Preserve the original's behavior. A migration is not a redesign: a safer design or a more consistent API is never grounds to diverge. An original that looks wrong is reported, and changing it is the planner's call. check: none reader: the parity review
The migration config
A migrating repository commits seal/parity.md, written from
templates/parity.md, which holds its fields. A machine-local checkout path
never goes in it: it lives in ~/.claude/specseal/parity-paths.md, keyed by
the origin remote URL, so worktrees and second checkouts resolve to one entry.
The original resolves in this order: the recorded path, a sibling directory of
the current repository, then a check by git remote -v against the declared
original. Where none resolves, the caller asks the user and records the
answer, and a reader that cannot ask returns original not found with what it
tried. A comparison against a guessed original proves nothing.
check: tests/test_review_axes.py
Three-way judgment
Where policy, the original and the new code diverge:
| Situation | Follow |
|---|---|
| Policy explicitly covers the divergence, and it holds up | Policy. Grounds means a quotable sentence with its source; "the document probably said so" is not grounds |
| Policy silent | The original, exactly |
| Grounds exist but look wrong | Neither silently: record both texts side by side and escalate |
Inherit before raising a product decision: where policy is silent and the original already does the thing, follow it and mark it decided, since only a rule in neither place needs a planner. check: none reader: the parity review
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 · -14 lines b07fcc4d1306
- 7d ago Changed · +16 lines · +5 tokens per session b7f6072ea7c9
- 11d ago Changed 9a9a6f2a9b94
- 14d ago Changed · -1 lines 7afaedf58bcb
- 1mo ago Changed · -1 tokens per session 5de2df1a9784
- 2mo ago First seen · 119 lines · 81 tokens per session scan A 0995df7928c6
legacy-parity is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 1,233 once invoked, about $0.0003 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
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
shipyard-debugging
Investigates root cause systematically before any fix is proposed. Use when encountering any bug, test failure, unexpected behavior, or error message. Also use for tracebacks, exceptions, "not working" complaints, build failures, performance problems, or integration issues, and whenever the next step would be to…
codebase-hygiene
Two-mode skill: (1) find semantic duplicates — functions doing the same thing under different names, invisible to copy-paste detectors; (2) deepen shallow modules — thin wrappers and pass-through layers that spread complexity. Advisory and read-only; changes route through BUILD with full gates.