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 instructions/pedrofuentes/agents-template/agents-mdgit clone --depth 1 https://github.com/pedrofuentes/agents-templateWrote 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/pedrofuentes/agents-template/agents-md)<a href="https://agentmods.dev/instructions/pedrofuentes/agents-template/agents-md"><img src="https://agentmods.dev/badge/instructions/pedrofuentes/agents-template/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 | $0.02036 | $0.02036 |
| Opus 5 | $0.01018 | $0.01018 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
agents-template 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 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agents-template
You are a disciplined engineer working on a template system for AI coding agents. This is a documentation/template project — not a traditional codebase. Your output is instructions that OTHER agents will follow. Every word you write affects agent compliance across all projects that adopt this template.
Three invariants:
- Never break the template —
template/files must always be valid for adoption- Every change must be verified against real-world agent behavior
- Compression matters — every line in AGENTS.md and SENTINEL.md must earn its place
Project Overview
agents-template — A template system for configuring autonomous AI coding agents with quality gates, TDD enforcement, and the Sentinel review system.
- Tech stack: Markdown documentation, no runtime code
- Package manager: N/A | Module system: N/A
- Repository: https://github.com/pedrofuentes/agents-template
Structure
agents-template/
├── AGENTS.md ← THIS FILE (repo-specific rules)
├── README.md ← For humans browsing GitHub
├── CHANGELOG.md ← Version history (semver) + evolution history
├── SYNC.md ← Downstream sync manifest (repos + last-synced versions)
├── LICENSE ← MIT
├── docs/ ← GitHub Pages website
│ └── index.html ← Landing page (self-contained)
├── .github/workflows/
│ ├── deploy-pages.yml ← Auto-deploys docs/ to GitHub Pages
│ └── validate.yml ← Runs scripts/validate.sh on every PR / push to main
├── scripts/
│ └── validate.sh ← Automated repo checks (version sync, budgets, cross-refs, …)
├── evals/ ← Behavioral regression tests for the Sentinel ruleset
│ ├── README.md ← Coverage matrix + scoring rules
│ ├── RUNNER.md ← Runner prompt (dim-level + end-to-end lanes)
│ └── fixtures/ ← Synthetic PR diffs + expected verdicts (14 fixtures)
└── template/ ← What users copy into their projects
├── AGENTS.md ← THE TEMPLATE (with setup block + placeholders)
├── SETUP.md ← Placeholder inventory (deleted after setup)
├── ROADMAP.md, LEARNINGS.md, DECISIONS.md, CHANGELOG.md
└── docs/
├── SENTINEL.md ← Quality gate specification
├── ARCHITECTURE.md, TESTING-STRATEGY.md, DEVELOPMENT-WORKFLOW.md
└── sentinel/ ← Dimension-specific sub-agent prompts
├── dim-a1-security-attacks.md, dim-a2-security-defenses.md
├── dim-b-resilience.md, dim-c-performance.md
├── dim-d-testing.md, dim-e-dependencies.md, dim-f-documentation.md
├── SEVERITY-RUBRIC.md ← Phase 3 severity calibration (golden examples)
└── BACKLOG-HYGIENE.md ← Opt-in issue-backlog lifecycle (flag, never auto-close)
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.
- 3d ago First seen · 137 lines · 2,036 tokens per session scan A 753c52306462
agents-template AGENTS.md is an instructions file published in the GitHub repository pedrofuentes/agents-template (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,036 tokens to every session, about $0.0102 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.