cc-research: Instructions file for Claude Code

AGENTS.md

cc-research AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from richer-richard/cc-research. It costs 962 tokens per session, scanned B, original, MIT.

A set of AGENTS.md instructions for the cc-research monorepo. A monorepo is one repository containing multiple related projects; these instructions explain its plugins, layout, conventions, and development rules.

In plain words
What is it for?
Guiding work on the Codex and Claude Code research plugins, including their files, versioning, builds, tests, and documentation.
Why use it?
It gives coding agents the project context needed to edit the correct plugin and follow the repository’s boundaries.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is richer-richard/cc-research's own configuration. It tells Claude Code, Codex and OpenCode how to work on cc-research itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-research configures →

Reuse

Borrowing it

Nothing to install: this file belongs to richer-richard/cc-research. 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/richer-richard/cc-research/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/richer-richard/cc-research

Made for: Claude Code, 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.

agentmods badge for cc-research AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/richer-richard/cc-research/agents-md/github.svg)](https://agentmods.dev/instructions/richer-richard/cc-research/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/richer-richard/cc-research/agents-md"><img src="https://agentmods.dev/badge/instructions/richer-richard/cc-research/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.

agentmods 80×15 button for cc-research AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/richer-richard/cc-research/agents-md"><img src="https://agentmods.dev/badge/instructions/richer-richard/cc-research/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 962 This file is loaded in full into every session.
When invoked 962 The same file — it is already loaded in full.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00962 $0.00962
Opus 5 $0.00481 $0.00481
Sonnet 5 $0.00192 $0.00192
Haiku 4.5 $0.00096 $0.00096

Measured 8d ago against content hash 77206669f5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

cc-research AGENTS.md scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Install locally: `codex plugin marketplace add <path-to-this-repo>` → `codex plugin add cc-research-codex` (or the `codex /plugins` browser). Enable hooks with `[features] hooks = true` and `[features] plugin_hooks = t
AGENTS.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Codex guide for the cc-research monorepo

This repository ships two independent deep-research plugins that share a method but no code:

  • Claude Code plugin in plugin/ + its Python Agent SDK front-end in sdk/. These are done and frozen — do not modify them except to update docs. They are versioned in lockstep (independent of the Codex plugin) and have their own marketplace at .claude-plugin/marketplace.json.
  • Codex plugin in plugin-codex/ (described here). An independent port for the Codex CLI that reproduces the same research method and the same on-disk evidence/audit substrate; only the platform plumbing differs. No shared core with the Claude plugin — the two are kept in sync by hand.

Codex plugin layout (plugin-codex/)

  • .codex-plugin/plugin.json — manifest (name cc-research-codex, version 1.2.0; points to skills/ and hooks/hooks.json).
  • skills/research/SKILL.md — the orchestrator method and the single source of truth for the Codex loop. Invoke with $research <query> or let Codex match it implicitly.
    • skills/research/references/{researcher,local-researcher,synthesizer}.md — the role contracts the orchestrator pastes into spawned subagents.
    • skills/research/agents/openai.yaml — invocation policy + UI metadata.
  • hooks/hooks.json — a Stop hook running scripts/audit.py.
  • scripts/audit.py — the Stop-hook citation/report audit (stdlib only; fail-open).
  • /.agents/plugins/marketplace.json — the Codex repo marketplace (entry cc-research-codex, source.path ./plugin-codex).
  • /.codex/agents/{researcher,local-researcher,synthesizer}.toml — optional typed subagents (repo-scoped). Plugins can't bundle subagents, so these are a convenience; the skill also works by pasting the contracts into ad-hoc subagents.

Conventions (match these when editing the Codex plugin)

  • Multi-agent is the point. The orchestrator fans out one researcher subagent per independent strand, in parallel (Codex agents.max_threads, default 6; keep it ≥ 5). Never collapse to single-agent sequential — that defeats the loop.
  • Evidence substrate (identical to the Claude plugin): each run writes runs/<id>/ with meta.json, plan.md, per-strand sources-<slug>.jsonl / claims-<slug>.jsonl (never merged), and report.md. In-body citations use the [#<source-id>] sigil and must resolve to a sources-*.jsonl id. Keep the A/B/C/D source tiering; every figure is a scored, tiered source row (no untiered "specific-detail" citations).
  • Codex built-in tools only: web_search, the shell + file edits, update_plan (progress), and natural-language subagent spawn (fan-out). No external research APIs, no MCP servers.
  • Two audit layers: the Stop hook (scripts/audit.py, fail-open; exit 2 + stderr = continuation) AND a mandatory in-skill self-audit in SKILL.md, so a missing/uncited report is caught even when hooks are off (plugin_hooks disabled or an untrusted directory).

Read the full file on GitHub · 31 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. 8d ago First seen · 31 lines · 962 tokens per session scan B 77206669f5f7

Subscribe to this mod's changes

cc-research AGENTS.md is an instructions file published in the GitHub repository richer-richard/cc-research (1 stars, last pushed 3mo ago), licensed MIT. It adds 962 tokens to every session, about $0.0048 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

next.js AGENTS.md

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

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 · 5,153 tokens

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 · 6,785 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

langchain AGENTS.md

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 · 4,469 tokens

spec-kit AGENTS.md

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 · 7,104 tokens