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 clawdotnet/openclaw.net --skill community-research-insightgit clone --depth 1 https://github.com/clawdotnet/openclaw.netWrote 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/clawdotnet/openclaw.net/community-research-insight)<a href="https://agentmods.dev/skills/clawdotnet/openclaw.net/community-research-insight"><img src="https://agentmods.dev/badge/skills/clawdotnet/openclaw.net/community-research-insight/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/clawdotnet/openclaw.net/community-research-insight"><img src="https://agentmods.dev/badge/skills/clawdotnet/openclaw.net/community-research-insight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.02511 |
| Opus 5 | $0.00020 | $0.01256 |
| Sonnet 5 | $0.00008 | $0.00502 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
community-research-insight 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community Research Insight Extractor
Extracts pain points, stakeholder needs, risks, and practical technology opportunities from community-engaged research discussions. Produces a structured insight brief for human review before publication.
What It Does
| Step | Kind | Purpose |
|---|---|---|
collect |
user_input |
Collect transcript, context, and audience via chat |
analyze |
llm_chat |
Extract grounded themes as structured JSON |
analyze_fallback |
llm_chat |
Produce best-effort grounded JSON if primary analysis fails |
draft |
llm_chat |
Draft the full 6-section insight brief as structured JSON |
validate |
llm_chat |
Gate preview on PASS vs REVISE grounding validation |
validation_revise |
llm_chat |
Explain why the brief is blocked when validation fails |
preview |
llm_chat |
Render validated findings as human-readable Markdown |
review |
user_input |
Pause for human approve/revise/reject decision |
final_response |
llm_chat |
Produce final output based on review decision |
Guardrails
- Never invent quotes, names, dates, or statistics.
- Never attribute views to named people unless present in the source.
- Never recommend replacing community engagement with automation.
- Always separate evidence from inference.
- Always flag missing information rather than filling gaps.
- Always require human review before publication or named attribution.
Fallback
If analyze fails (timeout, provider error, or JSON contract failure),
analyze_fallback runs a single-turn llm_chat on the same transcript and must
satisfy the same JSON output contract. If validate returns REVISE, the preview
path is blocked and validation_revise explains what must be fixed before human
review.
Output Contract
The analyze, analyze_fallback, and draft steps enforce OutputContract JSON
validation. The draft step requires executive_summary, key_pain_points,
stakeholder_needs, opportunity_map, risks_and_cautions, and
follow_up_questions.
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 · 318 lines · 41 tokens per session scan A ca81b20ef9ce
community-research-insight is a skill published in the GitHub repository clawdotnet/openclaw.net (498 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,511 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
simplify-code
Parallel 4-agent cleanup of recent code changes.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
dws
A command-line guide for DingTalk, a workplace platform with chat, documents, calendars, approvals, tasks, and other business tools.
planned-task-runtime
Handles system follow-up turns: planned-task-follow-up (synthesize, replan, build-workflow, checkpoint), background-task-completed, running-tasks context, and create-tasks silence rules. Load whenever any of these tags appear or after calling create-tasks.
planning
ONLY for coordinated multi-artifact work: multiple workflows with dependencies, shared data-table schema/migration across tasks, or the user explicitly asked to review a plan first. Load create-tasks via loadtool before calling it (search "create tasks" if not visible). Do NOT use for new one-off workflows…