agentmods.dev

do-it AGENTS.md

Repository instructions for do-it, a plugin that packages agent skills, checks, and helper agents for several coding tools from one source tree.

In plain words
What is it for?
Use them when contributing to do-it, especially when changing its skills, hooks, agents, commands, installers, or validation scripts.
Why use it?
They clarify which files are authoritative, how source differs from generated build files, and which language and file-size rules apply.

Instructions file for CodexOpenCode

27 21d ago A scan 873 tokens original MIT
View the source file tdwhere123/do-it
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/tdwhere123/do-it/agents-md
Clone the repo
git clone --depth 1 https://github.com/tdwhere123/do-it

Made for: Codex, OpenCode.

Per session 873 This file is loaded in full into every session.
When invoked 873 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 $0.00873 $0.00873
Opus 5 $0.00436 $0.00436
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00087 $0.00087

Measured 2d ago against content hash 37589fe31e29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

do-it 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 2d 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 · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical agent instructions for this repository. Behavioral rules live in the shipped layers — skills carry judgment (skills/do-it/do-it-code-quality), hooks carry numbers (hooks/write-quality-lint.sh), validators carry drift contracts (scripts/validate-*.mjs). This file holds only what cannot ship: repo-local facts for agents working on do-it itself.

File rules

  • Source and this file are English-only. Paired end-user docs stay bilingual (README.md / README.zh-CN.md, CONTRIBUTING.md).
  • Read and write source as UTF-8 without BOM.
  • Do not read files larger than 30 KB in full; use targeted reads or grep. (install/manage.mjs is over this limit.)

Repository

do-it is a cross-host agent-behavior plugin: skills, advisory/blocking hooks, and read-only subagents shipped to Claude Code, Codex, Cursor, OpenCode, Kimi Code, and Pi from one source tree.

Contribution rules (dogfood-first, issue-first, PR template) are load-bearing: CONTRIBUTING.md. Changes without an observed real-world problem get pushed back.

Source of truth vs build artifacts

Source of truth: skills/do-it/, hooks/, agents/*.toml, commands/, install/, scripts/, tests/.

Never edit build artifacts directly; rebuild them instead:

  • plugins/*/ — per-host bundles, regenerated by npm run build:generated plus node scripts/build-<host>-plugin.mjs (codex script writes plugins/do-it/).
  • index.json, plugins/*/skills/_index.md — generated indexes.
  • .do-it/runtime/ — session state; .pi-subagents/ — run artifacts.

Closed-set contracts

These drift checks run in npm test; touch one side and you must touch all:

  • Quality families — hooks/data/quality-families.tsv ↔ hooks/lib/write-quality-scan.sh ↔ skills/do-it/references/write-quality-families.md ↔ tests/hooks/ (validate:quality-families).
  • Keyword tables — hooks/data/*.tsv are data-only. Project overrides (<cwd>/.do-it/keywords.local.tsv, <git-root of edited file>/.do-it/write-quality.local.tsv) are data-only too: hooks read them line by line and never source project files. Precedence for numeric limits: env var > project file > default.
  • Hook JSON contract — hooks read host JSON on stdin and emit host-shaped JSON; a misconfigured environment must never crash a hook (advisory hooks exit 0).
  • Core single voice — hooks/data/execution-failure-modes.tsv (rule sentences) ↔ skills/do-it/do-it-core/SKILL.md (renders them) ↔ hook emission (router.sh, verification-gate.sh quote the TSV, never embed rule text) ↔ bridge constants (plugins/do-it-pi/extensions/index.ts, OpenCode bundle data) ↔ satellite skills cite core §<rule_id> instead of restating (validate:core-consistency).

Read the full file on GitHub · 79 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. 2d ago First seen · 79 lines · 873 tokens per session scan A 37589fe31e29

Subscribe to this mod's changes

do-it AGENTS.md is an instructions file published in the GitHub repository tdwhere123/do-it (27 stars, last pushed 21d ago), licensed MIT. It adds 873 tokens to every session, about $0.0044 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 2026-08-30.

agentic-workflowagentsai-agentscodexcodex-clideveloper-tools
Related

Other instructions, from other repositories

formkit CLAUDE.md

Instructions for formkit/formkit, covering formkit, architecture, packages, core (framework-agnostic) and vue integration.

formkit/formkit · 927 tokens

agentrq AGENTS.md

Instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, running tests, mcp server (backend/internal/controller/mcp/) and events (experimental).

agentrq/agentrq · 826 tokens

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.

alirezarezvani/claude-code-tresor · 5,338 tokens

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.

Lykhoyda/rn-dev-agent · 5,241 tokens

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).

OpenDigitalProductFactory/opendigitalproductfactory · 5,667 tokens

graflow AGENTS.md

Instructions for GraflowAI/graflow, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

GraflowAI/graflow · 757 tokens