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-worknpx skills add ChianW/C31 --skill c31-workgit 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-work)<a href="https://agentmods.dev/skills/chianw/c31/c31-work"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-work.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 | $0.00034 | $0.01477 |
| Opus 5 | $0.00017 | $0.00739 |
| Sonnet 5 | $0.00007 | $0.00295 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
C31-work 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 4d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | execute, work on, implement, 实现, 开发, execute-phase, run |
| ZH | 开干, 执行, 实现 |
| JA | 実装する, やろう, 開始する |
Output language: Respond automatically in the user's conversation language.
C31-work — Wave-Parallel Execution Engine
Input
$ARGUMENTS — A plan document path, a STATE.md path, or a bare work description.
Blank uses the latest plan doc or current directory STATE.md.
Workflow
Phase 0: Load & Triage
- Locate plan: read the plan file or parse STATE.md for
tasksandwaves. - Environment check: confirm git repo, branch name, clean working tree (stash if needed).
- Historical solutions search (new):
- Use
memory_searchto queryplan {task_type} {project_name}(e.g., "skill optimization compound") - If ≥1 relevant solution found (score > 0.5):
- Inject the relevant plan's Guidance + When to Apply + Examples into the current work context
- emit brief note:
📋 Found prior work record: {filename} — auto-injected as reference
- Adjust the wave grouping strategy based on historical solutions (e.g., if a certain task type requires special tooling, add it to Phase 0 checks upfront)
- Use
- Complexity routing:
| Complexity | Action |
|---|---|
| Trivial (1 file, no behavior change) | Execute inline, skip wave grouping. |
| Small (2–5 tasks) | Group into 1–2 waves, single worktree. |
| Medium+ (6+ tasks or cross-cutting) | Full wave analysis + parallel dispatch. |
Phase 1: Wave Analysis
Build a dependency DAG from the plan/STATE.md:
- Nodes: tasks (preserve U-IDs in subjects, e.g.
U3: Add parser coverage). - Edges:
depends_onfrom the plan, or inferred from file overlap (two tasks touching the same file are ordered by plan sequence). - Group into waves: all tasks with zero unresolved dependencies → Wave 1, then recurse.
Wave grouping rules:
- Wave 1: all independent tasks (no edges between them). Executed in parallel.
- Wave 2+: tasks whose dependencies are satisfied by prior waves. Executed sequentially per wave, waves ordered by dependency depth.
- File-collision guard: if two tasks in the same wave touch overlapping file paths, split the later one to the next wave.
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.
- 4d ago First seen · 142 lines · 34 tokens per session scan A b58d12f0cee4
C31-work is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 1,477 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.
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.
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.