agent-triage copilot-instructions.md

agent-triage copilot-instructions.md is an instructions file for GitHub Copilot from converra/agent-triage. It costs 262 tokens per session, scanned A, original, MIT.

A set of coding rules for agent-triage, a TypeScript tool that diagnoses how AI agents behave in production. It documents the project's patterns, structure, and testing commands.

In plain words
What is it for?
Use it when modifying agent-triage so suggestions follow its TypeScript, testing, prompt, trace-processing, and tool-registration conventions.
Why use it?
It gives an AI coding assistant the project context needed to suggest changes that fit the existing codebase.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/converra/agent-triage/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/converra/agent-triage

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for agent-triage copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/converra/agent-triage/copilot-instructions.svg)](https://agentmods.dev/instructions/converra/agent-triage/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/converra/agent-triage/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/converra/agent-triage/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 262 This file is loaded in full into every session.
When invoked 262 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00262 $0.00262
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured 3d ago against content hash 4bfef2c24c75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-triage copilot-instructions.md 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.

.github/copilot-instructions.md · 28 lines

What it actually says

Copilot Instructions for agent-triage

Project Context

agent-triage is a TypeScript CLI tool, MCP server, and library for diagnosing AI agents in production. It extracts behavioral policies from system prompts, evaluates traces, and generates diagnostic reports.

Code Style

  • TypeScript strict mode, ESM modules
  • Use .js extensions in import paths (TypeScript ESM convention)
  • Early returns, small functions, descriptive names
  • Conventional commits: feat:, fix:, test:, docs:

Key Patterns

  • All trace connectors normalize to NormalizedConversation from src/ingestion/types.ts
  • LLM calls go through createLlmClient() from src/llm/client.ts
  • Prompt templates in src/llm/prompts.ts return structured JSON
  • MCP tools use registerTool() with zod schemas
  • Tests use vitest, mock LLM responses, live in test/

When Suggesting Code

  • Prefer editing existing files over creating new ones
  • Follow the existing patterns in the nearest similar file
  • Add tests for new functionality in the corresponding test/ path
  • Run npm test and npm run lint to verify changes
Changes

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.

  1. 3d ago First seen · 28 lines · 262 tokens per session scan A 4bfef2c24c75

Subscribe to this mod's changes

agent-triage copilot-instructions.md is an instructions file published in the GitHub repository converra/agent-triage (4 stars, last pushed 5mo ago), licensed MIT. It adds 262 tokens to every session, about $0.0013 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.