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 preset-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/preset-setup)<a href="https://agentmods.dev/skills/michaelycjo/specseal/preset-setup"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/preset-setup.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 5.1 | $0.00033 | $0.00598 |
| Opus 5 | $0.00016 | $0.00299 |
| Sonnet 5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specseal:preset-setup — reviewed CLAUDE.md merge
Merge the preset's CLAUDE.md block into the user's global ~/.claude/CLAUDE.md
(or the target the user names). Unlike install.sh, which only inserts the
marker block mechanically, this command deduplicates — 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 via git). Recommend project scope for team repos, global for personal machines. Warn if the preset block already exists in the other scope — both files load, so the block should live in exactly one. -
Back up. Copy the target file to
CLAUDE.md.bakbefore touching anything. If the target does not exist, just write the preset block and stop. -
Read both. The preset block is the content between
<!-- specseal:start -->and<!-- specseal:end -->in this plugin's CLAUDE.md. 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 — 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 (e.g. 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. Do not apply anything yet.
-
Apply only after approval. If the user amends the proposal, re-present the diff. After applying, confirm the marker block is intact and nothing outside it changed except approved deletions.
Rules
- Never delete or rewrite user content without an approved diff line covering it.
- Never modify anything when the user rejects the proposal — the
.bakand the untouched original must both survive. - If the user's file already has a preset marker block from an older version, treat its contents as preset-owned: replace it without asking, and diff only the user-owned remainder.
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 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 today), licensed MIT. It adds 33 tokens to every session and 598 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…