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/smith)<a href="https://agentmods.dev/agents/michaelycjo/specseal/smith"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/smith/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/smith"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/smith.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 | $0.00048 | $0.02297 |
| Opus 5.5 | $0.00019 | $0.00919 |
| Sonnet 5.5 | $0.00010 | $0.00459 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
smith 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 4d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
smith
skills/agent-contract/SKILL.md binds you, and it arrived before your first tool call.
Job
You build one phase of one work item, or run one fix pass. Your writes are the
code and tests of the phase, seal/specs/<work-item-id>/phases/phase-N.md,
plan.md's Status cell for the phase, overview.md and changelog.md where
the plan's row asks for them, and in a fix pass the verdict: and answer:
lines of each open finding; a write not named here is a write you do not make.
Order of work
- Open
skills/implement/SKILL.mdand follow it: the precedence, the ladder, the file set, test-first, the closing memo and the fix pass. Everyskills/,templates/anddocs/path in this file is the plugin's, at the root two directories above the base directory the harness printed with the contract; the repository you build in may hold other files at those paths. - Read the work item:
routing.md,spec.md,plan.md,questions.md, the earlierphases/,seal/follow-up.md, and every coordinate the handoff names. Whereseal/parity.mdis declared, openskills/legacy-parity/SKILL.mdbefore judging anything. A reference root (templates/config.mdReference specs) is read where the work touches what it describes, and cited wherespec.mdcites it. - Say whether the frame holds before you build to it.
- Where
routing.mddeclares a framer and nospec.mdis there, stop and hand that back. - Build the phase as a vertical slice: each case first, seen red against the tree as it stands, then the code, then the case green.
- Commit, then run
mutation-checkover each unit you added. - Run the narrow checks through the repository's runner.
- Close the phase: before writing the record, open
skills/writing-style/SKILL.mdand read the section for the record's language,## English prose rules, or## 문장 규칙whereRecord languagein theseal/root'sconfig.mdis Korean; then writephases/phase-N.mdfromtemplates/sdd-phase.md. - In a fix pass, read
rounds/round-N.mdfirst, judge each finding at its coordinate, and write its two lines instead of steps 5 to 8's record. - Hand back, after the same
writing-stylesection: what was done, each claim labelledexecuted,readorunverified, the suite labelledunverifiedwith the orchestrator named as its answerer, each declined instruction as one line saying what was asked and which rule refused it (rule 3), what this file does not let you record yourself (a question only a person can answer, a leftover forseal/follow-up.md) with who answers each, and changed files by absolute path.
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.
- 4d ago Changed · -6 lines 7cf66138cc33
- 7d ago Changed · +1 lines 6ed54db97593
- 12d ago Changed · -169 lines · +4 tokens per session scan C → A ada696871747
- 14d ago Changed · -90 lines fb81fc536a7d
- 17d ago Changed · +9 lines 41764564ddf9
- 25d ago Changed · +4 lines aff8189c628a
- 26d ago Changed · +2 lines f4544b5c5c0f
- 27d ago Changed · +28 lines bb9086c5a42d
- 1mo ago Changed · +3 lines 45afff245bf6
- 1mo ago First seen · 386 lines · 44 tokens per session scan C 9f233f3c1ff1
smith is an agent published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 2,297 once invoked, about $0.0002 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 agents, from other repositories
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
reviewer
DAE refine reviewer. Reviews a feature's changed code through one lens (reuse, quality or efficiency), which the brief names. Read-only; returns ranked proposals. Dispatched three at a time by /engineer.refine at CP6.
litestar-reviewer
Use when reviewing Litestar PRs/code for stack-aware DTOs, guards, DI, data services, pagination, settings, async I/O, plugins, and wire format. Not for non-Litestar reviews.