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/514-labs/moosestack/agents-mdgit clone --depth 1 https://github.com/514-labs/moosestackWrote 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/514-labs/moosestack/agents-md)<a href="https://agentmods.dev/instructions/514-labs/moosestack/agents-md"><img src="https://agentmods.dev/badge/instructions/514-labs/moosestack/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 | $0.01794 | $0.01794 |
| Opus 5 | $0.00897 | $0.00897 |
| Sonnet 5 | $0.00359 | $0.00359 |
| Haiku 4.5 | $0.00179 | $0.00179 |
Grade C, and why
moosestack AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules && pnpm install How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Multi-language monorepo (Rust CLI + TypeScript/Python libraries) using PNPM workspaces, Turbo Repo, and Cargo workspace.
CRITICAL: When changing MooseStack functionality, ALWAYS run end-to-end tests. When changing user-facing features, add E2E tests to python-tests/typescript-tests templates AND audit documentation. Logs: ~/.moose/*-cli.log. Always format the code.
Build & Development Commands
All Languages
- Build all:
pnpm build(Turbo orchestrates builds) - Dev mode:
pnpm dev(starts dev servers) - Clean:
pnpm clean - Lint all:
pnpm lint - Format:
pnpm format(Prettier for TS/JS)
Rust
- Build:
cargo build - Debug CLI: Use debug build with verbose logging for ALL moose CLI commands:
Example:RUST_LOG=debug RUST_BACKTRACE=1 MOOSE_LOGGER__LEVEL=Debug ~/repos/moosestack/target/debug/moose-cli <command>RUST_LOG=debug RUST_BACKTRACE=1 MOOSE_LOGGER__LEVEL=Debug ~/repos/moosestack/target/debug/moose-cli init my-app typescript - Test all:
cargo test - Test single:
cargo test <test_name>orcargo test --package <package_name> --test <test_file> - Lint:
cargo clippy --all-targets -- -D warnings(REQUIRED pre-commit, no warnings allowed) - Format:
cargo fmt
TypeScript
- Test lib:
cd packages/ts-moose-lib && pnpm test(runs mocha tests) - Test single:
cd packages/ts-moose-lib && pnpm test --grep "test name pattern" - Typecheck:
cd packages/ts-moose-lib && pnpm typecheck
Python
- Test lib:
cd packages/py-moose-lib && pytest - Test single:
cd packages/py-moose-lib && pytest tests/test_file.py::test_function_name - Test pattern:
cd packages/py-moose-lib && pytest -k "test_pattern"
End-to-End Tests
- Run E2E:
cd apps/framework-cli-e2e && pnpm test(includes pretest: cargo build, pnpm build, package templates) - Single E2E test:
cd apps/framework-cli-e2e && pnpm test --grep "test name"
Testing Templates Manually
Templates cannot be run directly from within the repo—they must be initialized in a temp directory first. To test a template using the current branch's CLI and moose-lib versions:
# 1. Build the CLI
cargo build --package moose-cli
# 2. Package templates (creates tgz files with current template content)
node scripts/package-templates.js
# 3. Initialize template in a temp directory (outside the repo)
cd /tmp && ~/repos/moosestack/target/debug/moose-cli init my-test-app <template-name>
# 4. Verify the lockfile is up-to-date
cd /tmp/my-test-app && pnpm install
git status # Should show "nothing to commit, working tree clean"
If the lockfile changes after pnpm install, regenerate it in the template source directory:
cd ~/repos/moosestack/templates/<template-name>
rm -rf node_modules && pnpm install
# Commit the updated pnpm-lock.yaml
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 · 126 lines · 1,794 tokens per session scan C 59336af690f9
moosestack AGENTS.md is an instructions file published in the GitHub repository 514-labs/moosestack (588 stars, last pushed 1mo ago), licensed MIT. It adds 1,794 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
arandu CLAUDE.md
Instructions for vdittgen/arandu, covering arandu, architecture, top-level packages, commands and coding standards.
jesse AGENTS.md
AGENTS.md instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
AgentEval copilot-instructions.md
Copilot instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
mcp-ssh-manager CLAUDE.md
Claude Code instructions for bvisible/mcp-ssh-manager, covering claude.md, project overview, architecture, commands and setup and installation.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.