dwarves-kit AGENTS.md

Repository instructions that tell coding agents and people how to read the project, perform work, verify results, and know when to stop and ask. They also explain which safety checks only work in Claude Code.

In plain words
What is it for?
Use it to orient an agent at the start of a task, define a repeatable task-and-verification loop, and document when work is complete or needs clarification.
Why use it?
It gives different agents a shared way to work while making clear which rules are merely advice outside Claude Code. This prevents assuming that safety hooks work everywhere.

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/dwarvesf/dwarves-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/dwarvesf/dwarves-kit

Made for: Codex, OpenCode.

Per session 4,088 This file is loaded in full into every session.
When invoked 4,088 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 $0.04088 $0.04088
Opus 5 $0.02044 $0.02044
Sonnet 5 $0.00818 $0.00818
Haiku 4.5 $0.00409 $0.00409

Measured 2d ago against content hash 15744d73916c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dwarves-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 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 · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md: the operating layer

Tool-agnostic front door. Any agent runtime (Claude Code, Codex, Gemini, a human) reads this first to learn how work is done in this repo. It carries the portable operate-contract: what to read, how to run a unit of work, when work is done, and when to stop and ask.

Enforcement boundary (read this first)

This file is a contract, not a guardrail. Enforcement is Claude-Code-only: the hooks (safety-gate, push-to-main blocker, anti-rationalization Stop hook, the verification pipeline) are what actually block bad outcomes, and they run only under Claude Code. Under any other runtime (Codex, Gemini, a bare LLM) AGENTS.md is advisory only: it tells an agent what to do, but nothing enforces it. Do not assume the guardrails are portable. They are not, until the v3.x multi-runtime agent-hook work lands. See docs/PHILOSOPHY.md (honesty rule: never over-claim portable enforcement) and CLAUDE.md for the CC-specific layer (hooks, slash commands, plugin). The full layering contract, which hook backstops what and why (hard / advisory / convenience), is docs/architecture.md "Hook fallback layer".

The rest of this file is four portable zones. The goal-crafter (commands/assign.md) projects them into a six-section /goal (see "How a goal is composed" at the end).


1. Read in this order

Orient before you touch anything. Read top to bottom; stop when you have enough.

  1. AGENTS.md (this file) - how work is done here; the operate-contract.
  2. CLAUDE.md - the Claude-Code layer: stack, structure, rules, hooks, commands, plugin.
  3. docs/specs/SPEC-NNN-.md - the active spec; the shared contract for the cycle. Read its ## Verification and ## After state before implementing.
  4. docs/architecture.md / WORKFLOW.md / docs/data-flow.md - reference, not required per task. Read docs/architecture.md for how the pieces fit; docs/data-flow.md for how DATA moves (the signal path telemetry -> proposal -> board, the ledger write/read paths, the module map); read WORKFLOW.md for the lanes and the gate at each phase boundary, and its "Mega-goal delegate execution" section for how a multi-sub-goal mega-goal run dispatches (delegate mode: one fresh headless session per sub-goal; /goal stays the official outer loop either way).

Read the full file on GitHub · 185 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 · 185 lines · 4,088 tokens per session scan A 15744d73916c

Subscribe to this mod's changes

dwarves-kit AGENTS.md is an instructions file published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 4,088 tokens to every session, about $0.0204 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.