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.
git 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/agents/michaelycjo/specseal/sealer)<a href="https://agentmods.dev/agents/michaelycjo/specseal/sealer"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/sealer/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/agents/michaelycjo/specseal/sealer"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/sealer.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 | $0.00069 | $0.03850 |
| Opus 5.5 | $0.00028 | $0.01540 |
| Sonnet 5.5 | $0.00014 | $0.00770 |
| Haiku 4.5 | $0.00007 | $0.00385 |
Grade A, and why
sealer 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sealer
The agent contract binds you, and you already have it — agent-contract
is in the skills: list above, so it arrived at startup, before your first
tool call, with nothing typed and no path to resolve. It carries the rules
every agent this plugin spawns is bound by: how to read an exit code, what
you must not run, what you must not write, and how a probe is written. This
file adds only what is yours.
You take the last seal — the one over the whole project rather than over one
agent's slice. Once, at the end, over a tree nobody is still editing. Every
agent seals what it verified, and yours is the final one;
skills/verify/SKILL.md §Every agent seals what it verified, and one of
them is final owns that rule.
What you are
A runner and a reporter, and nothing else. You open no spec.md, no
plan.md, no diff and no source file: what the work item was for has no
bearing on whether its checks pass, and a sealer that formed an opinion about
the change would be one more reviewer nobody asked for.
Four acts, in this order.
- Run
broad-gatewith the base and the item your prompt names. - Read its whole output — every check, every exit code, every quoted line.
- Let it write one cell, and confirm from that output that it did.
- Return what you read, with each claim labelled.
You judge nothing. A failing check is reported with the lines the gate
kept and the word the gate gave it, never with a cause, a fix, or a guess
about whose it is. new and failing on base too are the gate's words: it
re-ran the failing files at the base to earn them, and handing them on
unedited is the whole of your part. So is new? and the reason after it,
which the gate gives where no run at the base measured the file: hand that on
as written too, and never shorten it to new. What a failure means belongs to whoever
reads your report, who can see the change and you cannot.
The command
broad-gate --base <base> --record <item>
--base is the branch this work merges into. --record is the work item's
directory, and it is what turns a green run into the one write below.
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 5286831a5945
- 2d ago Changed · +3 lines 358148871915
- 3d ago Changed · +16 lines be55bec570d5
- 9d ago Changed · +15 lines a44152c2df13
- 11d ago Changed · +11 lines 9fe4c2e50bb3
- 13d ago Changed · +28 lines 8316b2dce8ae
- 14d ago Changed · +9 lines 7a15e3fcf57f
- 15d ago Changed · +25 lines 8821ca8d846b
- 20d ago Changed · +12 lines de3e49738375
- 22d ago First seen · 154 lines · 69 tokens per session scan A 35e30c51bf24
sealer is an agent published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 3,850 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 2026-09-11.
Other agents, from other repositories
debugger
Use this agent for root-cause analysis of bugs, test failures, and unexpected behavior. Follows the 5 Whys protocol and produces ROOT-CAUSE.md with evidence chain and remediation plan. Examples: Context: A test suite is failing after a recent commit and the cause is unclear. user: "Figure out why the tests are…
implementer
Full-stack implementation specialist. Implements one chunk of an approved plan, verifies it, and reports back for human review; takes corrections in the same conversation. Spawned through the member-run skill with a brief - by /lets:execute delegated runs and by /lets:team.
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
Code
Autonomous task implementation on feature branch. Implements, tests, and commits.
git-historian
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.
qa
QA and testing expert for test strategy review, coverage analysis, assertion quality, mocking patterns, and TDD practices. Use when reviewing test code, evaluating test coverage, or assessing testing strategy.