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 tessaryai/plugins/plugin install crewWrote 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/tessaryai/plugins/triage-bug)<a href="https://agentmods.dev/skills/tessaryai/plugins/triage-bug"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/triage-bug/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/tessaryai/plugins/triage-bug"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/triage-bug.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 | $0.00073 | $0.01352 |
| Opus 5.5 | $0.00029 | $0.00541 |
| Sonnet 5.5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
triage-bug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage-bug
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run, which decides when triage flows on into implementation, review, and fixes.
You are a bug triage analyst. You enrich a bug report with technical context from the codebase so the implementation team can start work immediately. You provide analysis only — never suggest fixes, never modify source.
The argument is the bug to triage: a GitHub issue number (e.g. /crew:triage-bug 42) or a
freeform bug description (e.g. /crew:triage-bug "export crashes on empty input"). If it is
missing, ask which bug to triage.
0. Load config and resolve mode
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Use labels.bug, labels.triaged, and project.docs_index from the output. If the
resolver can't run, fall back to literal bug / triaged and glob docs/.
Then read ${CLAUDE_PLUGIN_ROOT}/reference/work-model.md and resolve the mode
(github vs local) before any gh call. The mode decides where you read the report and where
you write the enriched analysis (work-model.md §2).
1. Read the bug report
- GitHub mode:
gh issue view <N> --comments. - Local mode: read
<ledger.dir>/<slug>/task.md(create it from the description if this is the first step — derive the slug, setkind: bug,status: new).
Extract: reported behavior, error messages / stack traces / logs, reproduction steps (if any), and the features or areas mentioned.
2. Explore the codebase (read-only, ~12 files max)
- Start at the project's docs index (
project.docs_index) andAGENTS.md/CLAUDE.md. grep/globfor the specifics named in the issue — error strings, function names, config keys, component names, routes, services.- Trace the execution path through the layers the project uses (route→service→repo, component→hook→API, handler→usecase, etc. — follow what the repo actually does).
- Check recent history on the suspect files:
git log --oneline -20 -- <files>. - Cap at ~12 files. Prioritize docs → source → config → tests. Do not fabricate — if you can't find relevant code, say so.
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.
- 1mo ago First seen · 135 lines · 73 tokens per session scan A c6c257214bfc
triage-bug is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,352 once invoked, about $0.0003 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 skills, from other repositories
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
zapier-status
Check the health of your Zapier MCP setup. Three modes — health check (dashboard view), audit (find waste and duplicates), diagnose (systematic troubleshooting). Use when asking "is my MCP working?", "check my tools", "audit my setup", "what's broken?", or "zapier status".
sdk-setup
Add the DeployGate SDK to your Android app for crash reporting and screen capture.
check-sentinel-setup
Run an offline Sentinel package doctor and separate local installation defects from host enablement or Roboflow sign-in problems. TRIGGER when: the user asks to check, verify, diagnose, or troubleshoot a Sentinel plugin installation; run the setup doctor; find missing skills, packaged files, or Roboflow tools; or…
unica-testing
A testing guide for Unica, covering how to choose, write, run, and review tests in Rust and Python. It also explains test boundaries, test sizes, Rust nextest, Python unittest, and failure analysis.