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/glance)<a href="https://agentmods.dev/skills/iroha924/mumei/glance"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/glance/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/glance"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/glance.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 | $0.00142 | $0.00558 |
| Opus 5 | $0.00071 | $0.00279 |
| Sonnet 5 | $0.00028 | $0.00112 |
| Haiku 4.5 | $0.00014 | $0.00056 |
Grade A, and why
glance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Glance — one-line reliability summary
Surface the active feature's reliability in a single line so the user can check stability without context switching.
Trigger
User invokes /mumei:glance (no args) or /mumei:glance <feature>. The skill is disable-model-invocation: true; it never fires on the model's own initiative.
What it does
-
Resolves the target feature:
- no args → reads
.mumei/currentfor the active feature key - with args → uses the given feature key directly
- no args → reads
-
Computes pass^3 over the most recent 10 trials via
hooks/_lib/reliability.sh. -
Renders exactly one line to stdout:
<feature> | pass^3: <value-or-N/A> (n=<n_trials>, window=10, k=3) -
Outputs
no active featureto stdout (not stderr) and exits 0 when.mumei/currentis missing or stale (REQ-25.2.3).
How to invoke
Run the CLI implementation in scripts/mumei-glance.sh and print its stdout verbatim:
bash "$CLAUDE_PLUGIN_ROOT/scripts/mumei-glance.sh" "${1:-}"
The script always exits 0 (missing active feature is not an error). Do not reformat the output.
Don'ts
- Don't add headers, blank lines, or trailing commentary — the contract is one line.
- Don't emit
no active featureto stderr — REQ-25.2.3 specifies stdout. - Don't accept flags or multiple feature args. A single optional positional arg only.
- Don't re-interpret the numeric value — it is a window pass rate, not a geometric Pass^k.
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 · 47 lines · 142 tokens per session scan A 465bc623d945
glance is a skill published in the GitHub repository iroha924/mumei (2 stars, last pushed 2d ago), licensed MIT. It adds 142 tokens to every session and 558 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
harness
A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.
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.
generator-build-integrator
Internal Auto-Harness generator skill for worktree-merge build integration. Use only inside the parallel Generator integrator during build mode.