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 iroha924/mumei/plugin install mumeiWrote 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/iroha924/mumei/attest)<a href="https://agentmods.dev/skills/iroha924/mumei/attest"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/attest/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/iroha924/mumei/attest"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/attest.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 | $0.00134 | $0.00637 |
| Opus 5 | $0.00067 | $0.00318 |
| Sonnet 5 | $0.00027 | $0.00127 |
| Haiku 4.5 | $0.00013 | $0.00064 |
Grade A, and why
attest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Attest — detailed reliability view
Render the reliability snapshot for one mumei feature so the user can judge whether it is stable enough to ship or extend.
Trigger
User invokes /mumei:attest <feature> explicitly. The <feature> argument is a feature key — REQ-N-<slug> for spec vehicle, bare <slug> for plan vehicle. The skill is disable-model-invocation: true; it never fires from the model's own initiative.
What it does
- Reads the feature's
reliability-log.jsonl(prefers.mumei/specs/<feature>/over.mumei/plans/<feature>/). - Computes pass^3 over the most recent 10 trials (arithmetic mean of
passbooleans;N/Awhen fewer than 3 trials are recorded). - Renders three blocks to stdout:
- feature key
pass^3: <value-or-N/A> (n=<n_trials>, window=10, k=3)- markdown table of the last 10 rows (
wave,task_id,trial_n,pass,ts).
- Exits non-zero with
feature not found: <feature>to stderr if neither feature directory exists.
How to invoke
Run the CLI implementation in scripts/mumei-attest.sh and print its stdout verbatim:
bash "$CLAUDE_PLUGIN_ROOT/scripts/mumei-attest.sh" "$1"
The script handles the feature-not-found / missing-log / fewer-than-k-trials cases and writes the three blocks to stdout (errors to stderr). Do not reformat the output.
Don'ts
- Don't reinterpret the numeric
value— it is a window pass rate (arithmetic mean of pass booleans over the window), not a geometric Pass^k. Do not multiply, transform, or "explain it as a percentage". - Don't fall back to a different aggregator when the table is empty — the script's
N/Ais the contract. - Don't write to
reliability-log.jsonl— this skill is read-only. - Don't accept arguments other than a single feature key (no flags, no glob).
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.
- 9d ago First seen · 43 lines · 134 tokens per session scan A 74e70ff1e399
attest is a skill published in the GitHub repository iroha924/mumei (2 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 637 once invoked, about $0.0007 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
evaluator-write-qa-parallel
Internal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evaluator subagent during evaluatorqaparallel.
evaluator-write-qa
Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.
evaluator-write-retest-parallel
Internal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside the Evaluator subagent during evaluatorretestparallel.
evaluator-write-retest
Internal Auto-Harness evaluator skill for sprint retest and retest report writing. Use only inside the Evaluator subagent during retest mode.
evaluator-write-final-parallel
Internal Auto-Harness evaluator skill for parallel final QA report aggregation. Use only inside the Evaluator subagent during evaluatorfinalparallel.
generator-apply-fixes
Internal Auto-Harness generator skill for QA fix cycles. Use only inside the Generator subagent when it is addressing named defects from QA or retest.