Borrowing it
Nothing to install: this file belongs to jmfloreszazo/agent-eval-poc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmfloreszazo/agent-eval-poc/main/AGENTS.mdgit clone --depth 1 https://github.com/jmfloreszazo/agent-eval-pocWrote 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/instructions/jmfloreszazo/agent-eval-poc/agents-md)<a href="https://agentmods.dev/instructions/jmfloreszazo/agent-eval-poc/agents-md"><img src="https://agentmods.dev/badge/instructions/jmfloreszazo/agent-eval-poc/agents-md.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 5.1 | $0.00884 | $0.00884 |
| Opus 5 | $0.00442 | $0.00442 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
agent-eval-poc AGENTS.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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository agents
This repo ships three custom GitHub Copilot chat modes. They live under .github/chatmodes/ so VS Code Copilot picks them up automatically.
| Agent | Chat mode file | Purpose |
|---|---|---|
@corp |
.github/chatmodes/corp.chatmode.md | Governance gateway. The only agent you may invoke directly. Configures App Insights telemetry, opens the parent corp.case.run span, and dispatches to the two specialists. |
@fraud-analyst |
.github/chatmodes/fraud-analyst.chatmode.md | Forensic accounting analyst. Reads an accounting case and emits a strict-JSON verdict (fraud / clean / suspicious). |
@legal-counsel |
.github/chatmodes/legal-counsel.chatmode.md | Corporate counsel. Reads the case + the analyst verdict and emits a strict-JSON list of recommended legal actions. |
RULE 0 — never bypass @corp
GitHub Copilot Chat in the IDE does not export per-turn tokens,
prompts, model id or cost to your tenant. The only way for Compliance
and FinOps to see what an agent did is for every agent run to be
brokered by @corp, which:
- Configures OpenTelemetry → Application Insights.
- Opens a parent span
corp.case.runwithcase_id,ground_truth,actor,repo,run_id. - Calls
@fraud-analystthen@legal-counselthroughscenario-3/src/corp.pyso each turn produces onecorp.agent.invocationchild span withgen_ai.usage.*,corp.cost_usd(priced frompricing.yaml),corp.verdict.
No telemetry, no answer. If you invoke @fraud-analyst or
@legal-counsel directly, the run is ungoverned and will be flagged
by the governance evaluator.
Soft vs. hard control. That evaluator is a detective control — it flags an ungoverned run after the fact. The preventive control is the APIM gateway with locked egress and
disableLocalAuth(see scenario-3/docs/governance-architecture.md §3, "Precondición de integridad"). Convention alone does not stop a direct call to the model.
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.
- 7d ago First seen · 72 lines · 884 tokens per session scan A e084e421cc44
agent-eval-poc AGENTS.md is an instructions file published in the GitHub repository jmfloreszazo/agent-eval-poc (2 stars, last pushed 2mo ago), licensed MIT. It adds 884 tokens to every session, about $0.0044 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.