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 ChianW/C31 --skill c31-curatorgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/c31-curator)<a href="https://agentmods.dev/skills/chianw/c31/c31-curator"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-curator/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/chianw/c31/c31-curator"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-curator.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 | $0.00037 | $0.02863 |
| Opus 5 | $0.00018 | $0.01432 |
| Sonnet 5 | $0.00007 | $0.00573 |
| Haiku 4.5 | $0.00004 | $0.00286 |
Grade A, and why
C31-curator 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C31 Curator
Information curation and document generation skill. Takes the output of C31-research (facts) and C31-storm (judgments) and organizes them into deliverable documents.
Not just "formatting". Curation includes:
- Selecting what to include based on audience and purpose
- Structuring information for maximum impact
- Adding narrative flow (not just bullet points)
- Ensuring all claims have sources
- Generating multiple formats (email, report, outline) from same input
When to Use
- "把调研整理成文档"
- "帮我写一封套磁邮件"
- "把这个分析写成投资备忘录"
- "生成论文大纲"
- "整理成可以发给别人的格式"
- After C31-storm: "能不能写成..."
When NOT to Use
- User just wants quick judgment (C31-storm is enough)
- No prior research context (run C31-research first)
- User explicitly says "不用整理,告诉我重点就行"
Core Principles
- Audience-first — same content, different packaging for different readers
- Source-preservation — every claim in final doc must trace back to research
- Narrative flow — not a dump, a story with beginning, middle, end
- Moderator function — check if any important information was unused in prior stages
- Multiple formats — one input, many outputs (email, memo, outline, slide deck)
Pipeline
Input: C31-research findings + C31-storm synthesis + user intent (what document? for whom?)
↓
Phase 1: Purpose Clarification → what format? audience? tone?
↓
Phase 2: Content Selection → what to include, what to exclude, what to emphasize
↓
Phase 3: Moderator Check → what important info was unused in prior stages?
↓
Phase 4: Structure & Flow → organize into narrative with transitions
↓
Phase 5: Format Generation → produce the actual document
↓
Phase 6: Source Attachment → add citation list / traceability
↓
Output: Deliverable document + metadata
Phase 1: Purpose Clarification
Questions to resolve (ask user if unclear):
- Format: email / memo / report / outline / slide deck / social media post?
- Audience: who will read this? what do they care about? what's their prior knowledge?
- Tone: formal / casual / persuasive / informative / provocative?
- Length: one page / five pages / tweet-length?
- Action: what should reader do after reading? (reply, approve, think, share?)
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 · 337 lines · 37 tokens per session scan A 7df2135ca8b4
C31-curator is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 13d ago), licensed MIT. It adds 37 tokens to every session and 2,863 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 2026-08-31.
Other skills, from other repositories
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.