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 c31-1stgit 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/c31-1st)<a href="https://agentmods.dev/skills/chianw/c31/c31-1st"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-1st.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 | $0.00102 | $0.00949 |
| Opus 5 | $0.00051 | $0.00475 |
| Sonnet 5 | $0.00020 | $0.00190 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
C31-1st 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | C31-1st |
| ZH | 第一性原理, 追本溯源, 本质 |
| JA | 第一原理, 本質を探る |
Output language: Respond automatically in the user's conversation language.
First Principle Thinking
Trace back to the root, redefine — do not merely optimize.
Core Definition
First Principles Thinking is a method of breaking down complex things to the most fundamental physical or axiomatic facts, and then rebuilding solutions from those "ground truths" — rather than relying on analogy or imitating convention.
Analogical Thinking vs. First Principles
| Dimension | Analogical Thinking (conventional) | First Principles (ground-up innovation) |
|---|---|---|
| Starting point | Follow past experience, industry norms, or what others did | Strip away surface appearances and target the irreducible essential elements |
| Reasoning method | Inductive: others succeeded this way, so I'll do the same | Deductive: derive new solutions from fundamental laws and objective facts |
| End result | Incremental improvements and fine-tuning (optimizing what exists) | Innovative breakthroughs and reconstruction (redefining what exists) |
Classic Case: Elon Musk and SpaceX
Conventional thinking (analogical):
"Spacecraft have always been expensive — that's been true for decades. Buying a ready-made rocket is too costly, so lowering launch costs seems impossible."
First Principles:
"What are the core materials in a rocket? Aluminum, titanium, copper, carbon fiber. These raw materials are actually quite cheap on commodity markets — roughly 2% of the rocket's total price. So instead of buying finished products, we buy the raw materials and build it ourselves from scratch."
Result: Launch costs dropped to one-tenth or even one-hundredth of the original.
Practice Steps
When executing First Principles thinking, strictly follow these three steps:
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 · 84 lines · 102 tokens per session scan A 15c8ef7e0ab1
C31-1st is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 13d ago), licensed MIT. It adds 102 tokens to every session and 949 once invoked, about $0.0005 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.
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.