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-loopnpx skills add ChianW/C31 --skill c31-loopgit 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 | $0.00109 | $0.01836 |
| Opus 5 | $0.00055 | $0.00918 |
| Sonnet 5 | $0.00022 | $0.00367 |
| Haiku 4.5 | $0.00011 | $0.00184 |
Grade A, and why
c31-loop 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
C31-loop — Loop Engineering One-Click Setup
Purpose: C31 is a Loop-Ready Agent Harness. It already has State + Verification Chain + Knowledge Flywheel. This skill adds the scheduling layer (Schedule), making it a complete Loop Engineering System.
Hard Rules
- Ask only one question at a time — never combine multiple questions.
- Every question must provide options — reduce cognitive load for the user.
- Generate immediately after the interview — once all 5 questions are answered, generate all files without further confirmation.
- Generate means deploy — provide deployment commands that can be copied and pasted directly.
- Record decisions — write all 5 answers into
loop-adr.md, using the same ADR format as C31-grill.
Phase 1 — Interview (Strictly one question at a time, in order)
Opening statement (fixed):
◆ C31 Loop Setup — 5-Question Configuration Interview
I will ask you 5 questions, then automatically generate all configuration files and provide deployment commands.
You don't need to write any configuration manually.
Ready? Question 1:
Q1 — What task should this loop run?
What should this loop do?
A) daily-triage Scan issues/CI/commits daily and generate a report
B) dep-sweep Check for stale dependencies weekly and auto-open a PR
C) ci-watch Automatically analyze and attempt to fix CI failures
D) changelog Auto-generate release notes before each release
E) custom Custom task (I'll describe it)
Enter A/B/C/D/E:
→ Record the choice as LOOP_PATTERN
Q2 — How often should it run?
How often should this loop run?
A) Every weekday at 9 AM
B) Every 6 hours
C) On every push/PR
D) Every Monday at 9 AM
E) Custom (I'll describe it)
Enter A/B/C/D/E:
→ Convert the choice to a cron expression, record as LOOP_CRON and LOOP_TRIGGER
| Option | Cron | GitHub Trigger |
|---|---|---|
| A | 0 9 * * 1-5 |
schedule |
| B | 0 */6 * * * |
schedule |
| C | n/a | push + pull_request |
| D | 0 9 * * 1 |
schedule |
| E | user-provided | user-provided |
What ships with it
5 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 · 238 lines · 109 tokens per session scan A 63397a945365
c31-loop is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 7d ago), licensed MIT. It adds 109 tokens to every session and 1,836 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
pre-push
Runs the local equivalent of the CI merge gate before you push. Detects which areas (Python, TypeScript, docs) your changes touch, auto-fixes what it can, then runs only those checks. Use when the user asks to run pre-push checks, get push-ready, verify changes before pushing or opening a PR, "make sure CI will pass"…
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.