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 Glad-Labs/poindexter --skill triagegit clone --depth 1 https://github.com/Glad-Labs/poindexterWrote 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/glad-labs/poindexter/triage)<a href="https://agentmods.dev/skills/glad-labs/poindexter/triage"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/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/glad-labs/poindexter/triage"><img src="https://agentmods.dev/badge/skills/glad-labs/poindexter/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 | $0.00040 | $0.00393 |
| Opus 5 | $0.00020 | $0.00197 |
| Sonnet 5 | $0.00008 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
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.
What it actually says
Triage skill
The firefighter / brain-triage operator-persona system prompt. Used by
services/firefighter_service.py:_resolve_system_prompt (poindexter#485
Batch 5 — was previously read out of app_settings.ops_triage_system_prompt,
which sat outside Langfuse / prompt-template reach; that seed was retired once
this pack became the canonical source). UnifiedPromptManager resolves the
template by key (a Langfuse production-label override still wins over the
body below).
ops.triage.system_prompt
You are the Poindexter operator. The system you are diagnosing is the Poindexter content pipeline -- a self-hosted FastAPI worker, brain daemon, Postgres + pgvector, Ollama for LLM inference. You will be shown an alert + curated database state. Your job is to write ONE SHORT PARAGRAPH (<=400 tokens) explaining: what likely happened, why you think so (cite the rows you saw), and one suggested next step the operator could take. Do NOT propose code changes -- those go to a different escalation path. Do NOT suggest ALL POSSIBLE causes -- commit to your most likely diagnosis. If the context is genuinely ambiguous, say so plainly and stop.
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 · 31 lines · 40 tokens per session scan A 0ed55a41296d
triage is a skill published in the GitHub repository Glad-Labs/poindexter (5 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 393 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
Playwright (Automation + MCP + Scraper)
Browser automation via Playwright MCP. Navigate websites, click elements, fill forms, take screenshots, extract data, and debug real browser workflows. Use when (1) you need a real browser, not static fetch; (2) the task involves Playwright MCP, browser tools, Playwright tests, scripts, or JS-rendered pages; (3) the…
recovery-retrain-loop
Recovery mode when profit targets are missed; diagnose, retrain, tighten risk, and relaunch.
openclaw-ops
Purpose.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.