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.
npx skills add richer-richard/cc-research --skill researchgit clone --depth 1 https://github.com/richer-richard/cc-researchWrote 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.
[](https://agentmods.dev/skills/richer-richard/cc-research/research)<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.
<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>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 | $0.00062 | $0.02416 |
| Sonnet 5 | $0.00025 | $0.00967 |
| Haiku 4.5 | $0.00012 | $0.00483 |
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 10d 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.
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
Tasktool — you request the fan-out in plain language (see Parallel dispatch below). Concurrency is capped byagents.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 producereport.md. - plan — first token is exactly
planthen a query: do Scope + Plan only (writemeta.json+plan.md), then STOP. Do not retrieve. Setexpect_report:false. - resume — first token is exactly
resumethen a run id: re-openruns/<id>/, readmeta.json+plan.md+ any existingsources-*.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 aplan-only run), setexpect_report:trueinmeta.jsonso the Cite audit applies.
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.
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.
- 10d ago First seen · 126 lines · 0 tokens per session scan A 01b80cfc9068
research is a skill published in the GitHub repository richer-richard/cc-research (1 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 4,833 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
scout-consolidation
Launch a Scout consolidation session as a background process. Runs a lighter delta scan — captures what changed since the last run and updates action items and KB.
scout-briefing
Launch a Scout morning briefing session as a background process. Auto-detects mode (morning briefing, consolidation, or weekend briefing) from the current time and day.
scout-dream
Launch a Scout dreaming session as a background process. Processes feedback, does KB deep work, and works on wishlist items.
scout-research
Launch a Scout research session as a background process. Goes outward — discovers new information about KB entities via web search, docs, and APIs, then integrates findings.