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 agentmods add skills/chianw/c31/c31-devnpx skills add ChianW/C31 --skill c31-devgit clone --depth 1 https://github.com/ChianW/C31What 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 | $0.00128 | $0.02565 |
| Opus 5 | $0.00064 | $0.01282 |
| Sonnet 5 | $0.00026 | $0.00513 |
| Haiku 4.5 | $0.00013 | $0.00257 |
Grade A, and why
c31-dev 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 2d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C31-Dev — 完整开发流水线引导
Philosophy
Process over speed. Shared understanding before execution.
C31-Dev 不是"一键自动化",而是"有刹车的流水线"。每个阶段的用户确认是不可跳过的——这正是它存在的理由。
Pipeline 概览
┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
│ C31- │ ──→ │ C31- │ ──→ │ C31- │ ──→ │ C31- │
│ Grill │ │ Spec │ │ Plan │ │ LFG │
│ (拷问) │ │ (PRD) │ │ (蓝图) │ │ (执行) │
└──────────┘ └──────────┘ └──────────┘ └──────────┘
↑ ↑ ↑ ↑
用户确认 用户确认 用户确认 用户确认
"共识达成" "PRD OK" "Plan OK" "开干"
触发条件
- "我要做个…" / "我想开发…" / "I want to build..."
- "实现这个…" / "开发新功能"
- "走完整流程" / "pipeline" / "全流程"
- 任何从零开始构建软件/工具/功能的请求
Workflow
Phase 0: 初始化
步骤 0.1: 读取已有上下文
- 检查
memory/.planning/phases/是否有相关 PRD/Plan - 检查
memory/grill-sessions/是否有相关共识文档 - 搜索
memory/看是否有历史项目关联
步骤 0.2: 初始化状态
- 创建/读取
memory/.planning/pipeline-state-{project}.md - 标记当前阶段为
grill - 向用户说明 Pipeline 流程和确认门控机制
"进入 C31-Dev 流水线。我们会依次经过 Grill(需求拷问)→ Spec(PRD)→ Plan(技术规划)→ Work(执行)。每个阶段需要你的确认才能进入下一步。随时可以喊停。"
Phase 1: Grill(需求拷问 + 复杂度判定)
Grill 阶段同时承担复杂度判定职责——通过逐层拷问暴露隐藏假设,让真实复杂度自然浮现。不需要预评估。
步骤 1.1: 遵循 skills/C31-grill/SKILL.md 的完整流程:
- 一次一问,附带推荐答案
- 自动检测新术语、关键决策、记忆冲突
- 实时写入
memory/glossary.md和memory/decisions/
步骤 1.2: 复杂度判定(Grill 过程中自然浮现)
| 信号 | 含义 |
|---|---|
| 3-5 个问题后用户说"行了,很清楚了" | 项目简单,可能跳过 Spec 直接 Plan 或直接 Work |
| 多个分支都需要深入确认 | 标准流程:Grill → Spec → Plan → Work |
| 涉及架构变更、安全、外部依赖 | 深度流程:Grill 不跳过,Plan 需 CEDAR + STRIDE |
步骤 1.3: 共识确认
- 输出共识文档摘要
- 询问用户:"共识是否达成?进入 Spec 阶段,还是跳过直接 Plan/Work?"
- 选项:确认进 Spec / 跳过 Spec 直接 Plan / 跳过 Spec+Plan 直接 Work / 继续 Grill / 暂停
Phase 2: Spec(PRD 撰写)
激活条件:Grill 共识达成后,用户未选择跳过
步骤 2.1: 读取 Phase 1 的共识文档(如存在)和现有 REQUIREMENTS.md
步骤 2.2: 遵循 skills/C31-spec/SKILL.md 的 5 步流程:
- 必要时拦截"直接写代码"的冲动
- 渐进式披露 5 个问题
- 撰写 PRD →
memory/.planning/phases/XX-PRD.md - 验证门:成功标准可验证?边界非空?
- 生成 PLAN 骨架
What ships with it
2 files 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.
- 2d ago First seen · 206 lines · 128 tokens per session scan A def95ff05ec6
c31-dev is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 7d ago), licensed MIT. It adds 128 tokens to every session and 2,565 once invoked, about $0.0006 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.
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…
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.
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.