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/update)<a href="https://agentmods.dev/skills/michaelycjo/specseal/update"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/update/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/update"><img src="https://agentmods.dev/badge/skills/michaelycjo/specseal/update.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 | $0.02371 |
| Opus 5.5 | $0.00012 | $0.00948 |
| Sonnet 5.5 | $0.00006 | $0.00474 |
| Haiku 4.5 | $0.00003 | $0.00237 |
Grade A, and why
update 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specseal:update, take the release and see what is in it
The user runs this command; the session running it follows the procedure below and reports to the user. Two commands run in a fixed order, and neither of them says what the user is getting: run by hand they answer "you are now on ", which is a number, not a reason to reload or restart.
Procedure
1. Record what is running. Read the version from
$CLAUDE_PLUGIN_ROOT/.claude-plugin/plugin.json. This is the version this
session actually loaded, which is the one the user is comparing against.
2. Refresh the marketplace, then install.
claude plugin marketplace update specseal
claude plugin update specseal@specseal
Both, in that order. The first pulls the marketplace clone; the second installs from it. Run alone, the second reports already at the latest version against whatever the clone last knew: the failure is silent and looks like success.
If the second command reports it is already current, say so and stop. Nothing arrived, so there is nothing to load and neither move below is needed.
2b. Read the installed copy before believing the installer. The install path is keyed by the version string, and extraction is skipped when a directory by that name already exists. So on a machine that had one from an earlier numbering, the installer reports success, writes the right commit SHA beside it, and the copy that loads is whatever was already there. The summary in step 3 cannot see that, because it reads the marketplace clone, which is correct; it is the installed copy that is stale. Read the one path the installer records and compare:
p=$(python3 -c "import json,os;d=json.load(open(os.path.expanduser('~/.claude/plugins/installed_plugins.json'),encoding='utf-8'));print(d['plugins']['specseal@specseal'][0]['installPath'])")
grep -m1 '^## ' "$p/CHANGELOG.md" # must name the version step 2 reported
| Result | What happens |
|---|---|
| the heading names the version the installer reported | go on to step 3 |
| a mismatch | stop before step 3. The update did not land. Say so, name both versions (the one the installer reported and the one the installed CHANGELOG.md heads), and print the repair below for the user to type. Give no summary: a summary of what the user should be getting is exactly what makes this failure invisible |
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 · +2 lines · +1 tokens per session 5ac4ba5bce50
- 26d ago Changed · +3 lines 275d78aa6873
- 1mo ago Changed · +38 lines 5073bab12504
- 1mo ago Changed · +4 lines 39db537d09a1
- 1mo ago Changed · +27 lines ae480ff35d43
- 1mo ago Changed a571fcd720c0
- 2mo ago First seen · 114 lines · 30 tokens per session scan A 6a666f9788fb
update 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 2,371 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…