A multi-agent research workflow for questions that need information from many sources and a cited written report. It divides the question into separate research areas, compares the evidence, and combines the results.

Use it for deep research, comparisons, adoption decisions, and other questions that require several independent lines of investigation and citations.

It organizes broad research so evidence is gathered, checked against other findings, and preserved for later continuation.

research — Skill for Codex by richer-richard/cc-research

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.

Any agent

npx skills add richer-richard/cc-research --skill research

Clone the repo

git clone --depth 1 https://github.com/richer-richard/cc-research

Made for: Codex.

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/skills/richer-richard/cc-research/research/github.svg)](https://agentmods.dev/skills/richer-richard/cc-research/research)

Your own site

<a href="https://agentmods.dev/skills/richer-richard/cc-research/research"><img src="https://agentmods.dev/badge/skills/richer-richard/cc-research/research/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/skills/richer-richard/cc-research/research"><img src="https://agentmods.dev/badge/skills/richer-richard/cc-research/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,833 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00123	$0.04833
Opus 5.5	$0.00049	$0.01933
Sonnet 5.5	$0.00025	$0.00967
Haiku 4.5	$0.00012	$0.00483

Measured 2mo ago against content hash 01b80cfc9068, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research 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 2mo 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.

plugin-codex/skills/research/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cc-research — research method (the loop), Codex edition

This skill defines the orchestration loop. When it is active you are the orchestrator: you plan the work, spawn subagents in parallel to gather evidence, triangulate what they find, and have a synthesizer subagent write a cited report. You persist all evidence to disk so the run survives compaction and can be resumed.

This is an independent Codex port of the cc-research Claude Code plugin. It reproduces the same method and the same on-disk evidence/audit substrate; only the platform plumbing differs (Codex tools, subagent spawn, update_plan, the Stop-hook audit). There is no shared code with the Claude plugin.

Narrate every phase in plain prose to the user as you go — narration is the primary way progress is visible in the terminal. Use short status lines like the ones quoted in each phase below.

Subagents on Codex

You (the agent that adopted this skill) are the orchestrator.
You fan out to three roles, each defined by a contract file in this skill's references/ directory: researcher (web), local-researcher (local files), synthesizer (final report).
Codex spawns subagents in parallel when you ask it to, and collects their results in one response. There is no Task tool — you request the fan-out in plain language (see Parallel dispatch below). Concurrency is capped by agents.max_threads (default 6, so the ≤ 5 web researchers/wave below fit comfortably; recommend users keep it ≥ 5).
Subagents inherit the session model. Codex has no fixed Claude-style model tiers; if the repo ships typed agents in .codex/agents/{researcher,local-researcher,synthesizer}.toml, you may spawn those by name (they pin sandbox/model per role). Otherwise spawn ad-hoc subagents and paste the role contract into each one's instruction.

Modes (selected by the first token of the request)

full — <query>: run the whole loop and produce report.md.
plan — first token is exactly plan then a query: do Scope + Plan only (write meta.json + plan.md), then STOP. Do not retrieve. Set expect_report:false.
resume — first token is exactly resume then a run id: re-open runs/<id>/, read meta.json + plan.md + any existing sources-*.jsonl / claims-*.jsonl, and continue from the first unfinished phase. If you proceed past planning to produce a report (the normal case — e.g. resuming a plan-only run), set expect_report:true in meta.json so the Cite audit applies.

Read the full file on GitHub · 126 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 126 lines · 0 tokens per session scan A 01b80cfc9068

Subscribe to this mod's changes

research is a skill published in the GitHub repository richer-richard/cc-research (1 stars, last pushed 5mo ago), licensed MIT. It adds 123 tokens to every session and 4,833 once invoked, about $0.0005 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 2026-08-31.

Autonomous Agents Research agentic ai-agents anthropic citations claude

research next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
researchricher-richard/cc-research	Skill	1	5mo ago	MIT	A	123	Codex
returns-policystrands-agents/samples	Skill	925	yesterday	Apache-2.0	A	36	Claude Code
technical-troubleshootingstrands-agents/samples	Skill	925	yesterday	Apache-2.0	A	38	Claude Code
scout-askRaven-Scout/Scout	Skill	20	yesterday	MIT	A	131	Claude Code
scout-consolidationRaven-Scout/Scout	Skill	20	yesterday	MIT	A	36	Claude Code
scout-briefingRaven-Scout/Scout	Skill	20	yesterday	MIT	A	40	Claude Code
scout-dreamRaven-Scout/Scout	Skill	20	yesterday	MIT	A	29	Claude Code