agent-dev-kit AGENTS.md

Guidance for coding agents working in the agent-dev-kit repository. It explains the repository's instruction layers and how they fit together.

In plain words
What is it for?
Use it when an agent is working with or contributing to agent-dev-kit and needs to follow that repository's rules.
Why use it?
It prevents agents from confusing separate instructions about conversation style, project construction, workflow, safety checks, and orchestration.

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/lftpadilla/agent-dev-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Codex, OpenCode.

Per session 1,411 This file is loaded in full into every session.
When invoked 1,411 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 $0.01411 $0.01411
Opus 5 $0.00705 $0.00705
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured yesterday against content hash 3a4482108b3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-dev-kit 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 yesterday.

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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — how agents use this repo

Instructions for coding agents working in or with agent-dev-kit. Humans read the README; agents follow this file.

What this repo is

A public, generalist kit for directing coding agents. It ships curated skills, an adversarial /pr-review command, evals, overnight protocol templates, and orchestration profiles. The kit composes with optional private org skills overlays that live outside this git tree.

Layers (do not collapse them)

Layer Governs Where
caveman how the agent talks external plugin
ponytail what the agent builds external plugin
GSD how work flows (plan → execute → verify) external (get-shit-done-cc for Hermes; optional pi-gsd helper)
superpowers (guardrails) how code tasks are executed (TDD, root-cause debug, verification evidence) external (obra/superpowers)
dev-skills discrete capabilities plugins/dev-skills/AGENTS.md
ship / overnight / orchestration gates, isolation, long runs, and orchestration overnight-task-kit/AGENTS.md + Agent Tutor Orchestrator

Full map: docs/how-it-fits-together.md. External installs: docs/external-deps.md.

Toolchain preferences

  1. Prefer GSD for multi-step work (plan → execute → verify).
  2. Prefer treehouse (or equivalent) for isolated parallel agent worktrees.
  3. Prefer no-mistakes as a ship gate alongside /pr-review.
  4. Prefer gnhf as the overnight runner; treat overnight-task-kit/ as protocol and templates, not a second ralph-loop.
  5. Prefer AXI principles for agent contracts; prefer TOON for agent-facing structured output when the consumer is another agent or a token-sensitive channel. Use JSON when the consumer is a strict JSON API, a human-facing config file, or an existing schema that already requires JSON.
  6. Install extra skills via vercel-labs/skills (npx skills); reference lifecycle packs from addyosmani/agent-skills without vendoring them here.
  7. Prefer Tech Lead ($tech-lead) as the unified orchestrator and mentor for multi-agent workflows, GSD execution, and learning projects. Operates across learning (pedagogical tutor), flow (balanced), and autonomous (pure orchestration) modes.
  8. Prefer Agent-Native Repository Architecture (ANRS-1.0): Use lightweight Hub-and-Spoke AGENTS.md, declarative REGISTRY.yaml, and progressive disclosure. See docs/agent-native-architecture.md and REGISTRY.yaml.
  9. Prefer Superpowers execution guardrails (test-driven-development, systematic-debugging, verification-before-completion, receiving-code-review) during task implementation while keeping GSD authoritative for project lifecycle and state.

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 1,411 tokens per session scan A 3a4482108b3c

Subscribe to this mod's changes

agent-dev-kit AGENTS.md is an instructions file published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 1,411 tokens to every session, about $0.0071 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

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens