Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MichaelYcJo/SpecSeal/plugin install 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/preset-setup)<a href="https://agentmods.dev/skills/michaelycjo/specseal/preset-setup"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/preset-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/preset-setup"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/preset-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 | $0.00034 | $0.00635 |
| Opus 5.5 | $0.00014 | $0.00254 |
| Sonnet 5.5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
preset-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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specseal:preset-setup, a reviewed CLAUDE.md merge
The user runs this command, and the session running it merges the preset's
CLAUDE.md block into the user's global ~/.claude/CLAUDE.md, or into the
target the user names. install.sh only inserts the marker block; this
command also removes what the block duplicates, and every deletion goes
through the user first.
Procedure
-
Ask the scope first, unless the user already said: global (
~/.claude/CLAUDE.md, every project on this machine) or this project (./CLAUDE.md, committed, so teammates receive it through git). Recommend project scope for team repositories and global for a personal machine. Warn where the preset block already exists in the other scope: both files load, so the block lives in exactly one. -
Back up. Copy the target file to
CLAUDE.md.bakbefore touching anything. Where the target does not exist, write the preset block and stop. -
Read both. The preset block is the content between
<!-- specseal:start -->and<!-- specseal:end -->in this plugin'stemplates/claude-md-block.md($CLAUDE_PLUGIN_ROOT/templates/claude-md-block.md), the block's one source. Read the user's file in full. -
Classify each overlap between the user's existing content (outside any preset markers) and the preset block:
Finding Proposal Exact duplicate: same rule, same meaning Propose removing the user's copy (the block now owns it) Partial overlap: the user's rule is more specific Propose keeping the user's rule and note it overrides the block's general form Conflict: different values for the same concern (for example the response language) Ask which side wins. Never decide silently -
Present the result as a diff: the full proposed file, with each change annotated by its classification above. Apply nothing yet.
-
Apply only after approval. Where the user amends the proposal, present the diff again. After applying, confirm the marker block is intact and nothing outside it changed except approved deletions.
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.
- 7d ago Changed · -1 lines · +1 tokens per session 7014819840be
- 1mo ago Changed · +3 lines c835aed9aa7f
- 2mo ago First seen · 54 lines · 33 tokens per session scan A 108cad762c0a
preset-setup is a skill published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 635 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…