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-wizardnpx skills add ChianW/C31 --skill c31-wizardgit 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-wizard)<a href="https://agentmods.dev/skills/chianw/c31/c31-wizard"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-wizard.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 | $0.00076 | $0.01973 |
| Opus 5 | $0.00038 | $0.00986 |
| Sonnet 5 | $0.00015 | $0.00395 |
| Haiku 4.5 | $0.00008 | $0.00197 |
Grade A, and why
c31-wizard 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 5d 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.
**4. 机械验收收尾（最重要）。** 人执行完手动步骤后，**向导不许直接宣布成功**——必须有一个验证 stage 用机器手段实测结果（REST 探针 / curl 状态码 / 命令输出断言），全部通过才进 finish；不过就明确报错退出。人不宣告成功，机器验证。 How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard（C31 改良版 = 原生功能 1:1 + 四条增强）
功能上与 mattpocock/skills 的 wizard 完全等价：生成一个交互式 bash 向导，逐 stage 领着人走完一个手动流程（配置第三方服务、一次性迁移、装机）。模板库（template.sh 的 stage/banner/open_url/pause/ask/ask_secret/confirm/write_env/set_secret/set_var 库）一字不动——STAGES 标记以上的库代码绝不手改。
第零条 · 适用性闸门（原生第一条，优先级最高）
Don't invoke this for steps the agent can perform itself.
动笔前先回答：这个流程里哪些步骤只有人能做？Agent 能自己执行的——本机 shell、SSH 可达的服务器、有凭据的 API——agent 直接执行，不产出向导。向导只覆盖人独占的步骤：网页后台登录、手机/物理设备操作、OTP/人脸、无凭据的第三方面板。
实证（2026-08-12 教训）：VPS 部署网络代理服务——scp/ssh/跑脚本全程 agent 可做（免密密钥在本地），agent 直接非交互代跑（ssh 无 TTY + printf 管道喂 stdin 应答 banner/confirm，confirm 闸门由 agent 依据证据判断）；向导只该覆盖手机端 v2rayNG 导入这种真·人手步骤。
流程（与原生一致）
1. Scope —— 圈定流程
读仓库先行（不许冷问）：.env*、README、docker-compose、框架配置、.github/workflows/*（每个 secrets.*/vars.* 引用都是向导必须产出的值）。迁移类任务：现态、目标态、两者之间的不可逆操作。
然后把 stage 清单展示给用户确认——用户可增删改。
Done when: 每个 stage 已命名排序，且每个捕获值都知道 (a) 从哪拿 (b) 写到哪（.env / GitHub secret / 都不写——有些 stage 纯动作）(c) 是否敏感（隐藏输入）。
2. Map —— 每个 stage 的路线
精确到 "Dashboard → Developers → API keys → Reveal test key → copy"。不确定的 UI 路径或命令 → 问用户或查文档，禁止编造不存在的步骤。
Done when: 每个 stage 都能让陌生人照着走完。
3. Author —— 写向导
复制 template.sh 到目标路径，逐 stage 写。用库函数：stage/say/step/open_url/ask/ask_secret/write_env/set_secret/set_var/pause/confirm，设 TOTAL_STAGES。规矩：先 open_url 再问值；敏感值用 ask_secret；每个持久化值 write_env；set_secret 只给 CI 真需要的；不可逆操作 confirm 守门；每 stage 一件事（清屏后只有当前步骤）。
4. Verify & hand off —— 验证与交付
bash -n <script>；有 shellcheck 就跑chmod +x <script>- 不要自己端到端跑交互式向导（会开浏览器、阻塞等人输入）——静态追踪替代：每个值从哪来→落到哪，set_secret 名与 CI 引用逐一对应
- 告诉用户怎么跑；可复用的装机路径才提交进 repo 并链进 README，一次性向导用完可弃
C31 四条增强（stage 作者区内叠加，不碰模板库）
1. 读仓库配置代替问人。 向导启动时先从 .env / .env.local / 配置文件推导一切可推导的值（项目 ref、URL、key 名）。人只回答机器推不出的东西。问一个能自己查到的问题 = 向导作者偷懒。
SUPABASE_URL_VAL=$(_existing SUPABASE_URL || true) # _existing 是模板库自带
PROJECT_REF=$(printf '%s' "$SUPABASE_URL_VAL" | sed -E 's|https://([^.]+)\..*|\1|')
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.
- 5d ago First seen · 89 lines · 76 tokens per session scan A 95fe246a261c
c31-wizard is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 10d ago), licensed MIT. It adds 76 tokens to every session and 1,973 once invoked, about $0.0004 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
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
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…