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/muse)<a href="https://agentmods.dev/skills/iroha924/mumei/muse"><img src="https://agentmods.dev/badge/skills/iroha924/mumei/muse.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.01151 |
| Opus 5 | $0.00060 | $0.00575 |
| Sonnet 5 | $0.00024 | $0.00230 |
| Haiku 4.5 | $0.00012 | $0.00115 |
Grade A, and why
muse 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 8d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muse — auto-generate a feature retrospective
Produce a single markdown document summarising a finished mumei feature so the team builds institutional knowledge instead of forgetting what happened.
When to use
- The user invokes
/mumei:muse <feature>after/mumei:shelve. - The user invokes it on a
phase: donefeature before archival (rare; lets them edit the muse.md before shelve moves the docs).
This skill is disable-model-invocation: true — only fires on explicit user request. Never auto-trigger.
Inputs
The skill resolves the feature directory in this order:
.mumei/archive/*/<feature>/— archived feature.mumei/specs/<feature>/— spec vehicle, not yet archived.mumei/plans/<feature>/— plan vehicle, not yet archived
Refuse with a clear message if none match.
Method
feature="$1"
[[ -n "$feature" ]] || { echo "usage: /mumei:muse <feature>" >&2; exit 1; }
# Resolve feature dir.
feature_dir=""
for candidate in $(find .mumei/archive -maxdepth 3 -type d -name "$feature" 2>/dev/null) \
".mumei/specs/${feature}" \
".mumei/plans/${feature}"; do
if [[ -d "$candidate" ]]; then
feature_dir="$candidate"
break
fi
done
[[ -n "$feature_dir" ]] || { echo "feature not found: $feature" >&2; exit 1; }
# Cost-log backfill: if the feature has no cost-log.jsonl yet
# (older features may come up empty), try to recover the data from
# Claude Code's session logs. Always best-effort — graceful fail is
# mandatory. The script returns 0 even when no records can be
# recovered and writes a "partial backfill only" line to stderr.
cost_log="${feature_dir}/cost-log.jsonl"
if [[ ! -f "$cost_log" ]] || [[ "$(wc -c <"$cost_log")" -eq 0 ]]; then
bash "${CLAUDE_PLUGIN_ROOT}/scripts/cost-backfill.sh" "$feature_dir" || true
fi
# Delegate the heavy lifting to scripts/generate-muse.sh which knows
# how to read all the input files (including the now-possibly-backfilled
# cost-log.jsonl) and produce the markdown.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/generate-muse.sh" "$feature_dir"
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.
- 8d ago First seen · 105 lines · 119 tokens per session scan A b20edce9ecaf
muse is a skill published in the GitHub repository iroha924/mumei (2 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,151 once invoked, about $0.0006 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-review-contract-parallel
Internal Auto-Harness evaluator skill for parallel sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
evaluator-write-final-parallel
Internal Auto-Harness evaluator skill for parallel final QA report aggregation. Use only inside the Evaluator subagent during evaluatorfinalparallel.
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.