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 pcopu/coco --skill autoresearchgit clone --depth 1 https://github.com/pcopu/cocoWrote 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/pcopu/coco/autoresearch)<a href="https://agentmods.dev/skills/pcopu/coco/autoresearch"><img src="https://agentmods.dev/badge/skills/pcopu/coco/autoresearch/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/pcopu/coco/autoresearch"><img src="https://agentmods.dev/badge/skills/pcopu/coco/autoresearch.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 | $0.00020 | $0.00153 |
| Opus 5.5 | $0.00008 | $0.00061 |
| Sonnet 5.5 | $0.00004 | $0.00031 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
autoresearch 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 1mo 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.
What it actually says
Auto Research App
Use this app when you want Coco to study yesterday's activity in a topic against a specific outcome you care about.
Core behavior
- Ask for the outcome you want to optimize for in this topic.
- Review yesterday's Telegram-visible Coco session activity.
- Summarize what seemed to help, what created friction, and what matters most relative to the chosen outcome.
- Send a short morning note after 9am server-local time.
Notes
- This app is configured per topic through
/apps. - The first implementation keeps the analysis grounded in visible Coco chat history.
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.
- 1mo ago First seen · 22 lines · 20 tokens per session scan A 1ab4916ff64b
autoresearch is a skill published in the GitHub repository pcopu/coco (4 stars, last pushed 10d ago), licensed MIT. It adds 20 tokens to every session and 153 once invoked, about $0.0001 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.
Other skills, from other repositories
add-new-agent-support
Add a new agent (tool) support to agent-command-sync following the registry pattern.
debug
Systematic debugging with persistent state across context resets.
thread
Manage persistent context threads for cross-session work.
research-phase
Research how to implement a phase (standalone - usually use /gsd:plan-phase instead).
add-backlog
Add an idea to the backlog parking lot (999.x numbering).
workstreams
Manage parallel workstreams — list, create, switch, status, progress, complete, and resume.