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/aretw0/agents-lab/session-triagenpx skills add aretw0/agents-lab --skill session-triagegit clone --depth 1 https://github.com/aretw0/agents-labWrote 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/aretw0/agents-lab/session-triage)<a href="https://agentmods.dev/skills/aretw0/agents-lab/session-triage"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/session-triage.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 | $0.00035 | $0.00704 |
| Opus 5 | $0.00017 | $0.00352 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
session-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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Triage (Recente)
Use este skill quando o usuário disser que “já falou tudo no histórico” e quiser transformar conversas recentes em backlog executável.
Objetivo
- Ler histórico recente em modo local-first (por padrão: último 1 dia)
- Extrair pendências explícitas (Next Steps / In Progress / Blocked)
- Reconciliar com
.project/tasks(board canônico) - Produzir split operacional:
- Unlock swarm now (destrava throughput)
- Later stabilization (pode esperar)
Nota de arquitetura: o modo padrão usa sessões locais do projeto isolado (
.sandbox/pi-agent/sessions/<workspaceKey>) com janela tail-batch. O desenho alvo continua provider-agnostic (múltiplas plataformas), preservando o mesmo contrato de governança.
Fluxo recomendado
1) Snapshot rápido do histórico recente
pnpm run session:triage
Opcional JSON para automação:
pnpm run session:triage:json
Por padrão, a leitura é tail-batch (cauda da sessão) para economizar contexto.
Expansão progressiva quando necessário (sem scan completo de primeira):
node scripts/session-triage.mjs --days 2 --limit 12 --tail-lines 200 --window 2
node scripts/session-triage.mjs --days 2 --limit 12 --tail-lines 200 --expand
Fallback global é opt-in (evitar por padrão):
node scripts/session-triage.mjs --allow-global-fallback
2) Validar board canônico
project-status
project-validate
3) Reconciliar lacunas
- Se a pendência já existe em
.project/tasks, não duplicar. - Se não existe, criar task com ID novo e critérios claros.
- Não fechar task estratégica sem verificação/evidência.
4) Aplicar split operacional
- Unlock swarm now: P0, promotions pendentes, bloqueios e gaps que impedem materialização.
- Later stabilization: P1/P2, melhorias de ergonomia, extensões futuras.
Regras de governança
- Manter
no-auto-close - Exigir evidência (arquivos, comandos, resultados)
- Preservar
operator-in-the-loop - Evitar retrabalho de decisões já
decidedsem evidência nova
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.
- 4d ago First seen · 96 lines · 35 tokens per session scan A 8f14fffefcbb
session-triage is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 704 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 2026-08-30.
Other skills, from other repositories
pi-review-gated-delivery
Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.
omd-tickets
查看 omd pathfinder 当前地图前沿票,并拉取已落地的 AFK research 结果(pull 回流 + 预算内自续)。Trigger:/omd-tickets、前沿、看票、研究结果回来了吗。.
speckit-opsmill-retrospect
Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.
speckit-opsmill-summary
Produce a flow-level summary of the current Claude Code session — executive summary, chronological timeline, and outcomes — written into the active feature directory next to spec.md / plan.md.
speckit-auto-run
Run the full speckit workflow end-to-end — specify, plan, critique, tasks, implement, review, extract — making all decisions autonomously.
speckit-tinyspec-tinyspec
Generate a single lightweight spec file with context, plan, and tasks for small changes.