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/tomershahar/team-foundry/agents-mdgit clone --depth 1 https://github.com/tomershahar/team-foundryWrote 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/tomershahar/team-foundry/agents-md)<a href="https://agentmods.dev/instructions/tomershahar/team-foundry/agents-md"><img src="https://agentmods.dev/badge/instructions/tomershahar/team-foundry/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 | $0.00621 | $0.00621 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
team-foundry 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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - create-team-foundry
Project Overview
create-team-foundry is an open-source Node CLI (npx create-team-foundry) that scaffolds structured context files into any repo so AI coding tools (Claude Code, Gemini CLI, Cursor) can read team outcomes, decisions, and quality bars natively.
Tech stack: TypeScript, Node 18+, tsup (build), vitest (tests), @clack/prompts (interactive CLI)
Startup Rules
Before writing any code, complete in order:
- Read this file completely.
- Read
CLAUDE.mdfor project overview, design decisions, and quality standards. - Read
ARCHITECTURE.mdto understand the layer structure. - Read
PROGRESS.mdto find current iteration state and next steps. - Read
feature_list.jsonto see current feature status.
Do NOT run bash init.sh - it is currently empty.
Run Commands
- Install:
npm install - Build:
npm run build - Dev (watch):
npm run dev - Tests:
npm test- do not run this directly; share the command with the user and ask them to run it - Type check:
npx tsc --noEmit - Lint:
npm run lint
Hard Constraints
- All code must pass type checking before commit
- Do not commit broken builds
- TDD per iteration - tests must pass before an iteration is complete
- No silent writes - user always confirms before files are modified
- Generated content must read as written by a thoughtful senior PM, not a template
- Hell-yes standard: every file, coaching behavior, and onboarding question must be obviously essential or it's cut
Testing
- Tests live in
src/__tests__/ - Test runner: vitest
- Never run
npm testyourself - tell the user to run it and share output with you
Topic Docs
- Architecture - read before modifying any layer boundaries
- CLAUDE.md - source of truth for project design decisions
- PROGRESS.md - current iteration state and next steps
- feature_list.json - feature tracking
Definition of Done
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.
- 5d ago First seen · 64 lines · 621 tokens per session scan A d0d99212c441
team-foundry AGENTS.md is an instructions file published in the GitHub repository tomershahar/team-foundry (1 stars, last pushed 1mo ago), licensed MIT. It adds 621 tokens to every session, about $0.0031 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
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
cordon AGENTS.md
AGENTS.md instructions for ilyautov/cordon, covering working in this repository, the three invariants, the map, commands and tests.
everything-gemini-code GEMINI.md
Gemini CLI instructions for Jamkris/everything-gemini-code, covering project instructions, prompt defense baseline and guidelines.
eai-gofer GEMINI.md
Gemini CLI instructions for eai-support/eai-gofer, covering gemini.md and always-on eai contract.
shift-log CLAUDE.md
Claude Code instructions for re-cinq/shift-log, covering openspec instructions, integration tests and beads task tracking.
mcp-repo-onboarding AGENTS.md
Instructions for rogermt/mcp-repo-onboarding, covering agents.md — agent & copilot instructions, current status, output verification, project identity and ⚠️ critical: tdd required.