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.
git 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/commands/richer-richard/cc-research/research)<a href="https://agentmods.dev/commands/richer-richard/cc-research/research"><img src="https://agentmods.dev/badge/commands/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/commands/richer-richard/cc-research/research"><img src="https://agentmods.dev/badge/commands/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 | $0.00029 | $0.00773 |
| Opus 5 | $0.00015 | $0.00387 |
| Sonnet 5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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 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.
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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the cc-research orchestrator. Dispatch on the FIRST token of the arguments, then run the loop defined in the cc-research:research-method skill. Do not duplicate the method here — load and follow that skill.
Arguments: $ARGUMENTS
Dispatch (first-token rule)
Inspect the argument string:
- Begins with exactly
plan(the literal wordplan+ a space) → plan mode: run Scope + Plan on the remainder, writeplan.md, then STOP (do not retrieve). Setexpect_report:falseinmeta.json. - Begins with exactly
resume→ resume mode: the remainder is a run id; reopenruns/<id>/, readmeta.json+plan.md+ existingsources-*.jsonl/claims-*.jsonl, and continue from the first unfinished phase. - Anything else → full mode: treat the ENTIRE argument string as the research query and run the whole loop.
The words plan and resume are reserved only as the exact first token followed by a space. A query that merely contains them later (e.g. "how do teams plan sprints") is a normal full-loop query. If $ARGUMENTS is empty, ask the user for a query or run id and stop.
Run it
Invoke the cc-research:research-method skill and follow it exactly for the selected mode:
Scope → Plan → Retrieve (dispatch researcher / local-researcher subagents in parallel via Task, one per independent strand) → Triangulate / gap-check → optional wave 2 → Synthesize (synthesizer) → Cite → Package.
Follow the skill's Parallel Dispatch rule: derive the researcher count from the plan's independent strands and dispatch them in one batched set of Task calls — aim wide, up to the per-wave ceiling. Each researcher owns one strand and writes only its own sources-<strand>.jsonl / claims-<strand>.jsonl; the synthesizer cites source ids as [#<id>].
Narrate every phase in prose ("Planning N strands…", "Dispatching N researchers in parallel…", "Wave 1 done, M gaps, starting wave 2…", "Report written to runs//report.md"). Structural rails (overridable): maxTurns 60, ≤ 5 web researchers/wave, ≤ 2 waves, ≤ 8 tool calls/researcher, ≤ 3 local researchers. There is no default dollar cap — runs are uncapped unless the user sets one with --budget.
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.
- 8d ago First seen · 28 lines · 29 tokens per session scan A 4382a6c8838e
research is a command published in the GitHub repository richer-richard/cc-research (1 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 773 once invoked, about $0.0001 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 commands, from other repositories
scout-meta-review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
upgrade
Comprehensive dependency upgrade with security audit, prioritization, and validation.
review
Review proposed ADRs for lifecycle progression — accept implemented decisions, deprecate stale ones, archive trivial ones.
from-spec
Extract Architecture Decision Records from a completed spec.
types
Debug and fix TypeScript type errors with systematic analysis and expert guidance.