mint AGENTS.md

mint AGENTS.md is an instructions file for Codex, OpenCode from 3li7alaki/mint. It costs 1,158 tokens per session, scanned A, original, MIT.

A set of instructions for mint, a tool that records when a small coding task is allowed to be marked complete. Each unit has one goal, a list of files it may change, acceptance criteria, checks, and review categories.

In plain words
What is it for?
Use it to define and verify narrowly scoped changes, record attempts and evidence, and apply tests or other declared checks before completion.
Why use it?
It gives people and automated tools the same completion rules and keeps task records separate from the repository files. This makes the reason for calling work finished explicit and reviewable.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/3li7alaki/mint/agents-md
Clone the repo
git clone --depth 1 https://github.com/3li7alaki/mint

Made for: Codex, OpenCode.

Per session 1,158 This file is loaded in full into every session.
When invoked 1,158 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 9094b1fbd811, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 126 lines

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.

Read the full file on GitHub · 126 lines

Changes

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.

  1. 3d ago First seen · 126 lines · 1,158 tokens per session scan A 9094b1fbd811

Subscribe to this mod's changes

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.

Related

Other instructions, from other repositories