cladding AGENTS.md

Repository instructions for cladding, a multi-agent development harness that checks work through staged rules and drift detectors. They cover setup, verification commands, and coding style.

In plain words
What is it for?
Setting up cladding and running its tests, type checks, lint checks, and final repository validation.
Why use it?
They tell coding agents how to install, structure, and verify changes before pushing them.

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/qwerfunch/cladding/agents-md
Clone the repo
git clone --depth 1 https://github.com/qwerfunch/cladding

Made for: Codex, OpenCode.

Per session 1,250 This file is loaded in full into every session.
When invoked 1,250 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 $0.01250 $0.01250
Opus 5 $0.00625 $0.00625
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured yesterday against content hash 860a26e21704, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cladding 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the cross-tool entry point for any AI coding agent working on cladding (OpenAI Codex, Cursor, Cline, Aider, Continue, GitHub Copilot, Gemini CLI, JetBrains Junie, Windsurf, and the other tools that read the agents.md standard). Claude Code reads this too — there is no separate CLAUDE.md.

1. Project

cladding is the reference implementation of the Ironclad standard. Multi-agent dev harness; 15 Iron Law stages; 41 drift detectors; polyglot toolchain (9 languages). Successor to harness-boot.

2. Setup

End-user install:

npm install -g cladding

Contributor install (clones the repo and pulls dev dependencies):

git clone https://github.com/qwerfunch/cladding && cd cladding && npm install

Requires Node ≥ 20.

3. Verify before pushing

Run all four. The first three must pass cleanly; the fourth must be green (the 15-stage gate) on a clean working tree.

npm test
npm run typecheck
npm run lint
node bin/clad check

4. Code & comment style

Apply Google Style Guides for every language cladding supports, and the comment policy summarised below. The full per-language table and the six comment principles live in docs/code-style.md — that's the SSoT; this section is the entry pointer.

Comment policy in one paragraph: why over what, full doc-tag set on every export (TSDoc / JSDoc / pydoc / rustdoc / godoc / Javadoc), spec linkage via @see spec/features/F-NNN.yaml AC-NNN or @see ironclad-design/<section>.md whenever a decision traces to an external source, explicit invariants when non-obvious, self-documenting code first, no TODO markers / no date-bound notes / no comments that paraphrase the code.

5. PR policy

Branch off develop, never main. Open the PR against develop. The maintainer fast-forwards main only at explicit release time. Full contract: GOVERNANCE.md §4.3.

Read the full file on GitHub · 81 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 · 81 lines · 1,250 tokens per session scan A 860a26e21704

Subscribe to this mod's changes

cladding AGENTS.md is an instructions file published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 3d ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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.