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-plangit 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-plan)<a href="https://agentmods.dev/skills/chianw/c31/c31-plan"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-plan.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 | $0.00034 | $0.05596 |
| Opus 5 | $0.00017 | $0.02798 |
| Sonnet 5 | $0.00007 | $0.01119 |
| Haiku 4.5 | $0.00003 | $0.00560 |
Grade A, and why
C31-plan scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `kimi_search` | `exec` + `curl` | `RATE_LIMITED` persists | How it starts
The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | plan, 制定计划, 实现方案, 怎么实现, 分步, plan-phase, roadmap |
| ZH | 制定计划, 规划, 怎么实现, 分步 |
| JA | 計画を立てる, プランニング, 実装方法を考える |
Output language: Respond automatically in the user's conversation language.
C31-plan
Turn requirements into validated, executable plans. C31-brainstorm defines WHAT; C31-plan defines HOW — with coverage gates, wave analysis, and threat modeling.
Trigger
User says "plan", "制定计划", "实现方案", "怎么实现", "分步", "plan-phase", "roadmap", or any request to break down a task into an executable plan.
Inputs
Gather before proceeding. If not provided, ask:
- What to plan — task, goal, feature, or project. Accepts a feature description, a requirements doc path, a brainstorm output, or a bug report.
- Upstream document (optional) — path to a
*-requirements.mdorSTRATEGY.mdindocs/brainstorms/ormemory/.planning/. Read first; treat as source of truth. - Existing plan to deepen (optional) — identify target in
memory/.planning/phases/and short-circuit to Plan-Checker (Phase 5).
Core Principles
- Requirements as source of truth — Build from upstream docs; never re-invent behavior.
- Decisions, not code — Capture approach, boundaries, files, dependencies, risks, and test scenarios.
- Research before structuring — Explore codebase,
docs/solutions/,AGENTS.md,CLAUDE.md. - Nyquist validation — Map test coverage to every requirement before execution.
- Decision coverage gate (blocking) — Every
CONTEXT.mddecision must appear in the plan. - Package legitimacy gate — Audit external dependencies with
[OK]/[SUS]/[SLOP]tagging. - Right-size the artifact — Same philosophy at every depth.
- Separate planning from execution discovery — Resolve planning-time questions here.
- Keep the plan portable — Repo-relative paths only.
- Doubt-Driven Development — Every non-trivial decision must survive adversarial scrutiny before it enters the plan.
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.
- 6d ago First seen · 463 lines · 34 tokens per session scan A 87fed42b4037
C31-plan is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 11d ago), licensed MIT. It adds 34 tokens to every session and 5,596 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.