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-specnpx skills add ChianW/C31 --skill c31-specgit 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-spec)<a href="https://agentmods.dev/skills/chianw/c31/c31-spec"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-spec.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 | $0.00038 | $0.01334 |
| Opus 5 | $0.00019 | $0.00667 |
| Sonnet 5 | $0.00008 | $0.00267 |
| Haiku 4.5 | $0.00004 | $0.00133 |
Grade A, and why
C31-spec 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 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.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | spec, 写需求, PRD, 产品文档, 定义项目 |
| ZH | 写需求, 产品需求, PRD |
| JA | 仕様を書く, 要件定義, PRD作成 |
Output language: Respond automatically in the user's conversation language.
C31-spec — Spec-Driven Development Skill
Philosophy
Process not prose. Verification non-negotiable. Progressive disclosure.
Any new project, feature, or major change starts with a PRD. No exceptions. The PRD is the contract between intent and implementation. Writing it is cheaper than debugging what you should have decided upfront.
When to Activate
- User says: "I want to build...", "I want to develop...", "This project..."
- User jumps straight to implementation without defining scope
- Any task that will take >30 minutes or modify >3 files
- Any new skill, tool, or workflow
Workflow
1. Detect & Interrupt
If user skips spec and goes straight to code:
"Hold on. Write the PRD first, then write the code. That's the rule."
"Code without a PRD = unconstrained improvisation = rework."
2. Elicit Requirements (Progressive Disclosure)
Ask 5 questions, one at a time, in order:
- Goal: What problem does this solve? Who is the user? What is the success criterion?
- Command / Interface: How does the user invoke it? CLI command? API endpoint? Chat trigger word?
- Structure: What files / modules / tables are needed? What is the core data flow?
- Code style: Consistent with existing code conventions? What language / framework?
- Boundaries: Explicitly state what is not in scope. Resist scope temptations.
3. Write PRD
PRD template (required fields):
# PRD: [Project Name]
## Goal
- Problem statement (one sentence)
- Success criteria (2-3 verifiable items)
## Command / Interface
- How to trigger:
- Input parameters:
- Output format:
## Structure
- File list:
- Data flow:
- Dependencies:
## Code Style
- Language / Framework:
- Naming conventions:
- Integration points with the existing project:
## Testing
- How to verify "success criteria":
- At least 1 test case:
## Boundaries (explicitly excluded)
- Not doing X:
- Not doing Y:
- If the user requests these later, a new PRD must be opened
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.
- 5d ago First seen · 165 lines · 38 tokens per session scan A c31929d64f75
C31-spec is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 10d ago), licensed MIT. It adds 38 tokens to every session and 1,334 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.
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.
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.