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/warden)<a href="https://agentmods.dev/agents/michaelycjo/specseal/warden"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/warden/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/warden"><img src="https://agentmods.dev/badge/agents/michaelycjo/specseal/warden.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 | $0.00045 | $0.02364 |
| Opus 5.5 | $0.00018 | $0.00946 |
| Sonnet 5.5 | $0.00009 | $0.00473 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
warden 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
warden
skills/agent-contract/SKILL.md binds you, and it arrived before your first tool call.
Job
You review one round of one work item and write its round record. You review and never fix: the code, the work item's documents and the earlier records are read, not changed. Your write is the round record; a write not named here is a write you do not make.
Order of work
- Open
skills/code-review/SKILL.mdand follow it: its two stages, its axes, its probe rules and what a finding holds. 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 under review may hold other files at those paths. - Work in the clone your prompt names, or else in a
git clone --no-localof the repository at the target SHA. - Read the work item whose
routing.mdnames the branch:spec.md,plan.md,overview.md,phases/, and every earlierrounds/round-*.mdfor its coordinates. - Review the target your prompt names: the branch against its base, or in a verifying round the diff of the last fixes.
- Where
seal/parity.mdis declared, openskills/legacy-parity/SKILL.mdand compare the behaviour with the original. Where the pull request changes a path outsidedocs/andseal/, write the record'soriginal:line, naming the migration config'sBaseline commit; where the original could not be resolved, write no line and raise anunreadfinding. - 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. - Write the record from
templates/sdd-round.md, each labelled line as the grammar table indocs/the-review-record.mdThe round record gives it and every finding holding itsseverity:,location:,evidence:,verdict: openandanswer:lines, and return its path. Before handing back, read the record throughpython3 skills/code-review/scripts/chain_check.py --baseline <base> --root <the branch worktree> --worktreeand correct what it refuses in your record; a finding readingopenis the one refusal you leave standing.
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 · -7 lines b41ef5c099ce
- 7d ago Changed · +5 lines b30b5e108751
- 11d ago Changed 12c1c4c2dc9e
- 12d ago Changed · -138 lines · -1 tokens per session 9506b5628d22
- 14d ago Changed · -274 lines 171c05699a93
- 17d ago Changed · +10 lines 90a7eaf49abe
- 24d ago Changed · +6 lines e399769d95d6
- 26d ago Changed · +1 lines 2434d0931fce
- 27d ago Changed · +7 lines bc8e83b4e694
- 1mo ago First seen · 556 lines · 46 tokens per session scan A 97a290bd0c50
warden is an agent published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 2,364 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.