What is ccswarm AGENTS.md?

A project instruction guide for working on ccswarm, a Rust-based multi-agent system. It explains the project structure, coding rules, security practices, and checks to run.

Use it when changing ccswarm code, especially its session and workflow components. It also guides formatting, linting, testing, documentation, and secret handling.

It gives coding agents the project’s rules and workflow in one place, reducing misplaced code, unsafe practices, and missed verification steps.

How nwiizo/ccswarm configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nwiizo/ccswarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nwiizo/ccswarm/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nwiizo/ccswarm

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nwiizo/ccswarm/agents-md/github.svg)](https://agentmods.dev/instructions/nwiizo/ccswarm/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nwiizo/ccswarm/agents-md"><img src="https://agentmods.dev/badge/instructions/nwiizo/ccswarm/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nwiizo/ccswarm/agents-md"><img src="https://agentmods.dev/badge/instructions/nwiizo/ccswarm/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 560 This file is loaded in full into every session.

When invoked 560 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00560	$0.00560
Opus 5.5	$0.00224	$0.00224
Sonnet 5.5	$0.00112	$0.00112
Haiku 4.5	$0.00056	$0.00056

Measured 12d ago against content hash 311fcf14a6e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ccswarm 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 12d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ccswarm Codex Guide

Goal

ccswarm is the workflow, governance, A2A, and provider execution layer. Keep terminal/session primitives, provider output parsing, and persistence in crates/ccswarm/src/session; keep workflow orchestration in crates/ccswarm/src/workflow.

Read First

CLAUDE.md
docs/ARCHITECTURE.md
docs/APPLICATION_SPEC.md

Build And Verify

cargo fmt --all
cargo clippy --workspace -- -D warnings
cargo test --workspace
cargo run -p ccswarm -- --help

Project Rules

Write comments, rustdoc, commit messages, and markdown docs in English.
Prefer Result<T, E> with thiserror; avoid .unwrap() in production code.
Prefer Rust-native patterns already used in this repo: type-state, channels, iterator pipelines, and actor-style isolation where they improve clarity.
Keep workflow logic out of low-level session helpers.
Keep tests focused on core behavior instead of growing broad fragile suites.
Never hardcode secrets. Use environment variables and SensitiveString when handling API keys.

Codex Assets

Repo skills live in .agents/skills/.
The bundled nwiizo-coding-style skill is copied from nwiizo/dotfiles, including its references, metadata, and license. Preserve those resources together when refreshing the copy.
Development and architecture rules live in .agents/rules/, with matching copies in .claude/rules/ and .codex/claude/rules/. Update all three together.
Custom subagents are defined in .agents/agents/*.toml and registered from .codex/config.toml.
The original Claude configuration is mirrored under .codex/claude/ for reference.
Detailed project rules remain available in .codex/claude/rules/*.md.

Available Subagents

frontend-specialist
backend-specialist
devops-specialist
qa-specialist
rust-fix-agent
code-refactor-agent
architecture-reviewer
all-reviewer
review-fix-agent

Recommended Codex Skills

review-fix: review the current diff, fix clear issues, then re-run cargo clippy --workspace -- -D warnings and cargo test --workspace --no-run. This is the repo-local Codex counterpart to the personal home-self-review workflow.

Read the full file on GitHub · 66 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.

12d ago Changed · +5 lines · +86 tokens per session 311fcf14a6e1
1mo ago First seen · 61 lines · 474 tokens per session scan A e05bca610ef7

Subscribe to this mod's changes

ccswarm AGENTS.md is an instructions file published in the GitHub repository nwiizo/ccswarm (153 stars, last pushed 8d ago), licensed MIT. It adds 560 tokens to every session, about $0.0022 per session on Opus 5.5. 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.

vscode buildNext.instructions.md

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 · 9,649 tokens

ccswarm: Instructions file for Codex