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.
npx skills add kensaurus/mushi-mushi --skill mushi-triagegit clone --depth 1 https://github.com/kensaurus/mushi-mushiWrote 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/kensaurus/mushi-mushi/mushi-triage)<a href="https://agentmods.dev/skills/kensaurus/mushi-mushi/mushi-triage"><img src="https://agentmods.dev/badge/skills/kensaurus/mushi-mushi/mushi-triage/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/kensaurus/mushi-mushi/mushi-triage"><img src="https://agentmods.dev/badge/skills/kensaurus/mushi-mushi/mushi-triage.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 | $0.00034 | $0.00621 |
| Opus 5 | $0.00017 | $0.00311 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
mushi-triage 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mushi Triage Workflow
Use this skill to investigate a user-felt bug report end-to-end using the Mushi MCP server.
When to use
- User reports a bug and you want a complete picture before writing code
- A Mushi report ID is available and you want to understand root cause, evidence, and blast radius
- You want to see whether a similar bug was fixed before and what the fix looked like
Triage workflow
Run these steps in order. Do not call dispatch_fix until you have confirmed the fix scope with the user.
Step 1 — Discover projects (if project ID unknown)
list_projects
Pick the relevant project from the returned list.
Step 2 — Get project context
get_project_context { project_id: "<id>" }
Review SDK heartbeat, ingest status, and open report counts.
Step 3 — Survey the triage queue
get_recent_reports { status: "open", limit: 10 }
Identify the report you want to investigate. Note the id.
Step 4 — Deep evidence pull
get_report_evidence { report_id: "<id>" }
Read screenshot URL, console logs, network requests, and user comments. Form a working hypothesis.
Step 5 — Full triage orchestration
triage_issue { report_id: "<id>", project_id: "<id>", include_logs: true }
This combines report detail, similar bugs, fix context, blast radius, and recent pipeline logs into one packet. Read recommended_actions carefully.
Step 6 — Fix context (if a previous fix attempt exists)
get_fix_context { reportId: "<id>" }
Check what the previous fix attempt did and why it may have failed.
Step 7 — Pipeline logs (if something looks broken on the Mushi side)
get_pipeline_logs { project_id: "<id>", level: "error", limit: 20 }
Step 8 — Dispatch fix (explicit user confirmation required)
Only after discussing findings and getting confirmation:
dispatch_fix { reportId: "<id>", autoReadyPr: false }
autoReadyPr: false keeps the PR as a draft for review before it can merge.
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.
- 12d ago First seen · 92 lines · 34 tokens per session scan A 65c84a31166a
mushi-triage is a skill published in the GitHub repository kensaurus/mushi-mushi (3 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 621 once invoked, about $0.0002 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
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
tracely
Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…
bug-hunter
Precision-first adversarial bug hunting for runtime, logic, data, concurrency, and security defects. Uses deterministic risk triage, evidence-bounded retrieval, Hunter/Skeptic/Referee review, optional hybrid verification, and explicit immutable Fixer scope. Scan-only and single-pass by default; complete-coverage…
hunter
Deep behavioral code analysis agent for Bug Hunter. Performs multi-phase scanning to find logic errors, security vulnerabilities, race conditions, and runtime bugs. Uses doc-lookup (Context Hub + Context7) for framework verification. Reports structured JSON findings.