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 agentmods add skills/michaelycjo/specseal/code-reviewnpx skills add MichaelYcJo/SpecSeal --skill code-reviewgit 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/code-review)<a href="https://agentmods.dev/skills/michaelycjo/specseal/code-review"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/code-review.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.05760 |
| Opus 5 | $0.00056 | $0.02880 |
| Sonnet 5 | $0.00023 | $0.01152 |
| Haiku 4.5 | $0.00011 | $0.00576 |
Grade A, and why
code-review 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 today.
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 — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-review — spec first, then quality
Loaded by the warden agent; also drives the orchestrator running a
review. The default assumption is "this code has defects" — try to find
them, not to prove their absence. An ungrounded LGTM is forbidden; when
uncertain, write a question, not a pass.
The language the round records are written in
The prose in rounds/round-N.md — its cell contents and the text beneath its
tables — follows Record language in config.md, English when the row is
absent. The root is <repo>/seal/ where that directory exists and
$(git rev-parse --git-common-dir)/seal/ otherwise.
What stays English regardless: every field name, section heading and
vocabulary word the checkers match, listed in templates/config.md under
What no row governs. chain_check.py reads those strings literally, so a
translated ## Verdicts or Verdict column is not a translation — it is a
record the checker cannot read.
The report you post to the pull request is not a record. It is prose for
whoever opens that pull request, and follows Commit and pull request language instead, per commit-pr-convention. Posting and recording are
separate acts producing different texts, which is why the two rows split
here.
Two stages, in order
- Spec compliance — actual code vs. the written spec (
docs/policies first, thenseal/specs/SDD). Look for both missing and unrequested extra behavior. Do not trust the implementer's report; read the code. - Quality — only after stage 1 passes: correctness, error handling, security, performance, test quality.
The SDD set includes the work item's overview.md, which arrives in the diff
rather than needing a search — the change writes it. It is the implementer's
account, so stage 1 governs it: read the code, never adopt what it concludes.
Three sections carry that account. Where spec and implementation diverged
declares where the code left the document; Not verified is the author's own
list of claims nobody has checked; Fed back into the spec holds clauses the
implementer added to the spec set during this change, which is why an account
citing them is citing itself.
Settle what you can and report each result; what only a person can answer stays
open, and the report says which of the two happened. Reviewers do not edit the
file.
What ships with it
1 file 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.
- today Changed · +227 lines bb0a619d2138
- 4d ago First seen · 209 lines · 113 tokens per session scan A 7526faaf0458
code-review is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 5,760 once invoked, about $0.0006 per session on Opus 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
tooluniverse-drug-research
Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
catalyst-center-readonly
Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…
build-audit-logs
Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…