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 agentmods add skills/tessaryai/plugins/triage-bugnpx skills add tessaryai/plugins --skill triage-buggit clone --depth 1 https://github.com/tessaryai/pluginsWrote 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.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 | $0.00073 | $0.01352 |
| Opus 5 | $0.00036 | $0.00676 |
| Sonnet 5 | $0.00015 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
triage-bug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
triage-bug
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run, which decides when triage flows on into implementation, review, and fixes.
You are a bug triage analyst. You enrich a bug report with technical context from the codebase so the implementation team can start work immediately. You provide analysis only — never suggest fixes, never modify source.
The argument is the bug to triage: a GitHub issue number (e.g. /crew:triage-bug 42) or a
freeform bug description (e.g. /crew:triage-bug "export crashes on empty input"). If it is
missing, ask which bug to triage.
0. Load config and resolve mode
python3 "${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.
- 3d 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 2d ago), licensed MIT. It adds 73 tokens to every session and 1,352 once invoked, about $0.0004 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
collab-conflict
까다로운 동료·소통빌런과 부딪힐 때 감정 상하지 않게 대응하고 거리를 지키도록 도와주는 스킬입니다. '이 사람 어떻게 대하지', '자꾸 떠넘기는 동료', '거절하는 법', '직장 인간관계 스트레스', '갈등 대응'처럼 말하면 됩니다. 유형별 대응 전략, 감정과 사안 분리, 정중한 거절, 관계 거리 두기로 직장 갈등을 소모전이 아니라 관리 가능한 문제로 바꿉니다.
collab-negotiation
1:1 면담을 준비하고, 상대를 설득하거나 무언가를 요청·협상할 때 대화를 설계해 주는 스킬입니다. '면담 준비해줘', '이거 어떻게 설득하지', '연봉 협상 어떻게', '부탁하는 법', '정중하게 요청하고 싶어'처럼 말하면 됩니다. 면담 목표 설정 → 상대 입장 파악 → 설득 구조 → 요청·거절 화법 → 합의·후속의 5단계로 관계를 지키며 원하는 걸 얻는 대화를 만듭니다.
collab-feedback-loop
피드백을 건설적으로 주고, 받은 피드백을 감정 상하지 않게 소화하도록 도와주는 스킬입니다. '피드백 어떻게 줘야 해', '부정적 피드백 받았는데 속상해', '피드백 전달하는 법', '중간 점검 요청하고 싶어'처럼 말하면 됩니다. SBI 구조로 건설적 피드백을 설계하고, 받은 피드백을 사실과 감정으로 분리해 소화하며, 먼저 피드백을 요청하는 법까지 다룹니다.
collab-meeting
회의가 산으로 가지 않게 아젠다를 짜고 결론까지 끌고 가는 진행을 도와주는 스킬입니다. '회의 아젠다 짜줘', '이 회의 어떻게 진행하지', '회의가 자꾸 산으로 가', '의사결정 회의 준비', '회의록 정리'처럼 말하면 됩니다. 목적 정의 → 아젠다 설계 → 진행 규칙 → 의사결정 → 회의록·후속 액션의 5단계로 결론이 남는 회의를 설계합니다.
collab-productivity-report
직장에서 제출하는 주간업무보고를 빠르게 작성해주는 스킬입니다. '주간보고 작성해줘', '이번 주 한 일 정리', '주간업무보고', '팀장님께 보낼 보고', '한 주 업무 리뷰'처럼 말하면 됩니다. 한 주 성과·진행 중 일·이슈·다음 주 계획을 정해진 틀로 정리하고, 격식체/구어체 톤까지 맞춰 보고서 초안을 만들어줍니다.
corezoid-lifecycle
Safely pauses, resumes, or moves existing Corezoid processes and folders. Use only when the user explicitly asks to pause/unpause/resume/activate a process or to move/relocate/reorganize a specific process or folder. Trigger on "pause process", "resume process", "move process", "move folder", "поставь процесс на…