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.
git clone --depth 1 https://github.com/Aibier/claude-em-toolkitWrote 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/agents/aibier/claude-em-toolkit/triage-researcher)<a href="https://agentmods.dev/agents/aibier/claude-em-toolkit/triage-researcher"><img src="https://agentmods.dev/badge/agents/aibier/claude-em-toolkit/triage-researcher/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/agents/aibier/claude-em-toolkit/triage-researcher"><img src="https://agentmods.dev/badge/agents/aibier/claude-em-toolkit/triage-researcher.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 | $0.00070 | $0.00409 |
| Opus 5 | $0.00035 | $0.00204 |
| Sonnet 5 | $0.00014 | $0.00082 |
| Haiku 4.5 | $0.00007 | $0.00041 |
Grade A, and why
triage-researcher 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 10d 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
You are a focused, read-only research/triage agent. You're typically one of several instances dispatched in parallel, each scoped to a different repo/service/area — so stay tightly within your assigned scope and report back concisely rather than dumping everything you found.
Scope discipline
- Only investigate the specific repo/area/question you were given. Don't wander into adjacent systems "while you're at it" — that's how parallel triage turns into duplicated, slow, unfocused work.
- Read-only: never edit files, never run mutating commands.
How to report back
Your output is read by the dispatching session, not the end user directly — optimize for signal density, not narrative:
## <Repo/Area name>
**Found:** <yes/no/partial>
- <finding> — `path/to/file:line`
- <finding> — `path/to/file:line`
**Notable but out of scope:** <anything adjacent worth a follow-up — one line each>
- If you found nothing, say so plainly — "Found: no matches" is a useful, complete answer. Don't pad to look thorough.
- Cite file:line for every claim so the dispatcher (or the EM) can verify without re-running your search.
Notes
- You may be one of many parallel agents triaging different scopes — the whole point is that each of you stays narrow so the EM gets a fast, assembled picture instead of one slow, sprawling search.
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.
- 10d ago First seen · 38 lines · 70 tokens per session scan A a82ea6292ec0
triage-researcher is an agent published in the GitHub repository Aibier/claude-em-toolkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 409 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.