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-researchgit 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-research)<a href="https://agentmods.dev/skills/chianw/c31/c31-research"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-research.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02370 |
| Opus 5 | $0.00018 | $0.01185 |
| Sonnet 5 | $0.00007 | $0.00474 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
C31-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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | research, 调研, 最佳实践, 资料, 研究, how should I |
| ZH | 调研, 研究, 最佳实践 |
| JA | 調査する, リサーチ, ベストプラクティス |
Output language: Respond automatically in the user's conversation language.
C31 Research
Unified research skill. Covers best practices, framework documentation, git history, community issues, institutional memory, and bug reproduction. All modes are read-only — does not write code.
When to Use
- "What is the best practice?" / "idiomatic way" / "how should I..."
- Before entering an unfamiliar tech stack
- Debugging framework-level errors / verifying version changes
- Bug reports lacking reproduction steps / "Have we solved something similar before?"
- Checking health of a new dependency before adoption
- Understanding historical context before modifying complex code
Core Principles
- Read-only — never write code, never modify files.
- Source hierarchy — official docs > community consensus > blog posts.
- Version-sensitive — always note framework/library version; docs drift.
- Explicit gaps — say "not found" rather than guess.
- Output ≤80 lines + one code example max.
Research Fallback Chain (Auto-Downgrade — No User Interruption)
If any mode encounters missing data or an error during execution, auto-downgrade in the following order. Never stop to ask the user.
IF official docs not found → search community consensus (HN / StackOverflow / official Discussions)
IF community consensus not found → search blogs / RFCs / talk slides (with ⚠️ caveats)
IF all sources exhausted → explicitly state "Insufficient evidence" + output list of sources searched
IF version mismatch → flag deprecation risk, continue with latest version, note "User version unverified"
IF search timeout → return partial results + mark in gaps: "Search timed out: did not cover [X]"
IF 5 search attempts yield nothing → flag as gap, stop exhaustive search
What ships with it
1 file 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.
- 8d ago First seen · 214 lines · 36 tokens per session scan A 435a5c47423c
C31-research is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 13d ago), licensed MIT. It adds 36 tokens to every session and 2,370 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
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.
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…
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.