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/3li7alaki/mint/agents-mdgit clone --depth 1 https://github.com/3li7alaki/mintWhat 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 | $0.01158 | $0.01158 |
| Opus 5 | $0.00579 | $0.00579 |
| Sonnet 5 | $0.00232 | $0.00232 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
mint 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mint: atomic completion ledger contract
Drivers organize and execute work. mint records why an atomic unit is allowed to be called done.
mint is driver-, agent-, and user-agnostic. A human shell, CI job, SlayZone card, or any other driver uses the same commands and clears the same floor. mint never launches agents, manages tickets, owns terminals, or creates and removes Git worktrees.
One unit, one claim
A unit contains one goal, an explicit can-modify scope, observable EARS acceptance criteria,
and its declared gates and review lenses. Create it through the CLI:
mint spec new "harden token validation" --slug harden-token \
--goal "Reject empty tokens" --scope "src/auth/**,tests/auth/**" \
--acceptance "WHEN an empty token is supplied, THE system SHALL reject it" \
--gate "tests: go test ./..." --reviews "security,adversarial"
The JSON response contains the unit ID and absolute spec path. Specs are operational state, not repository files.
State and worktrees
mint writes no .mint directory and never edits .gitignore. State lives at:
$MINT_STATE_HOME/repos/<repo-id>/worktrees/<worktree-id>/{units,attempts,receipts,notes}
Without MINT_STATE_HOME, the base is $XDG_STATE_HOME/mint, or
~/.local/state/mint. Repository identity comes from the canonical common Git directory.
Worktree identity comes from the canonical worktree root and worktree Git directory. Linked
worktrees therefore aggregate under one repository while keeping all mutable evidence isolated.
There is no repo-local compatibility reader or migration path.
Attempts and provenance
An attempt is one bounded effort against a unit. Initialize it with generic provenance:
mint exec init harden-token 001 --attempt maker-1 \
--executor codex --vendor openai --model gpt-5 \
--locality remote --execution-ref driver-run-42
executor, vendor, model, locality, and executionRef are opaque attributable claims.
A driver may add --observed-by and --attestation; mint stores them but owns no executor
registry, binary adapter, default executor, or process lifecycle. Typed provenance is declared
evidence, not authenticated identity. observedBy and attestation improve attribution only to
the strength of the supplying driver's trust boundary.
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 · 126 lines · 1,158 tokens per session scan A 9094b1fbd811
mint AGENTS.md is an instructions file published in the GitHub repository 3li7alaki/mint (10 stars, last pushed 22d ago), licensed MIT. It adds 1,158 tokens to every session, about $0.0058 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
formkit CLAUDE.md
Instructions for formkit/formkit, covering formkit, architecture, packages, core (framework-agnostic) and vue integration.
agentrq AGENTS.md
Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.
rn-dev-agent AGENTS.md
Instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.
Forge-Agentic-Coding-CLI CLAUDE.md
Instructions for hoangsonww/Forge-Agentic-Coding-CLI, covering claude.md, identity of this repo, build & verify commands (canonical), repository map and conventions.
opendigitalproductfactory AGENTS.md
AGENTS.md instructions for OpenDigitalProductFactory/opendigitalproductfactory, covering dpf — agent rulebook, 1. first principles, 2. project architecture, 3. branching, commits & prs and 4. verification — build gate (mandatory).