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-sxsgit 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-sxs)<a href="https://agentmods.dev/skills/chianw/c31/c31-sxs"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-sxs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chianw/c31/c31-sxs"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-sxs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00098 | $0.01058 |
| Opus 5 | $0.00049 | $0.00529 |
| Sonnet 5 | $0.00020 | $0.00212 |
| Haiku 4.5 | $0.00010 | $0.00106 |
Grade A, and why
c31-sxs 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | c31-sxs |
| ZH | 四寻思观, 寻思, 解构 |
| JA | 四尋思観, 解体する |
Output language: Respond automatically in the user's conversation language.
C31-sxs: Four Inquiries (四寻思观)
Core Function
Guide the user through the Yogācāra "Four Inquiries" (四寻思观) to deconstruct a specific emotion, event, or attachment across four layers. The goal is not to eliminate the emotion, but to let its "reality" be deconstructed — revealing that it is merely an arising of dependent conditions, a conventionally designated name with no fixed essence.
Trigger Recognition
Activate when the user explicitly says any of the following words, or asks to "deconstruct / analyze / contemplate" a particular anxiety, attachment, or emotion:
- sxs
- c31-sxs
- 四寻思 / 四寻思观 (Four Inquiries)
- 寻思 (inquiry / contemplation)
- Asks to process a thought "through the Four Inquiries"
Workflow
- Confirm the target: Ask the user what object they wish to inquire into (a specific event / emotion / thought).
- Guide layer by layer: Follow the order Name → Event → Essence → Discrimination. Ask one question per layer, and wait for the user's response before moving to the next.
- No judgment: The user's answers do not need to be "correct" — they only need to be honest. Do not correct the user's philosophical understanding; only advance the process.
- Close out: After all four layers, give the user an integrative reflection — pointing out which layer they seemed most stuck on, or where a new space opened up after something was peeled away.
Four Inquiries Question Templates
For any specific object the user presents (e.g., "anxiety about the Kyoto application", "fear of bankruptcy", "I got angry at someone"), ask in this order:
1. Name Inquiry (名寻思)
The word you used (e.g., "failure" / "anxiety" / "rejection") — does it point to a single fact, or are multiple things mixed together? If you unpack it, what distinct components are actually inside?
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.
- 9d ago First seen · 73 lines · 98 tokens per session scan A a82d27a7f725
c31-sxs is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 14d ago), licensed MIT. It adds 98 tokens to every session and 1,058 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.
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.