agentmods.dev

ainumbers: Skill for Claude Code

.claude/skills/wave-checklist/SKILL.md

wave-checklist is a skill for Claude Code from PostOakLabs/ainumbers. It costs 38 tokens per session (1,613 once invoked), scanned A, original, MIT.

A repository workflow and completion checklist for building tools and finishing development waves. It covers required project files, validation commands, index updates, and rules for generated files.

In plain words
What is it for?
It is for following the repository's build process, running pre-flight validation, updating the tool grid, and completing a wave of work.
Why use it?
It reduces missed checks and inconsistent project metadata before changes are pushed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is PostOakLabs/ainumbers's own configuration. It tells Claude Code how to work on ainumbers itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ainumbers configures →

not rated 11repo yesterday A scan 38 tokens original MIT
View source ↗ PostOakLabs/ainumbers ainumbers.co
Reuse

Borrowing it

Nothing to install: this file belongs to PostOakLabs/ainumbers. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PostOakLabs/ainumbers/main/.claude/skills/wave-checklist/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PostOakLabs/ainumbers

Made for: Claude Code.

Wrote 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.

agentmods badge for wave-checklist

README.md
[![agentmods](https://agentmods.dev/badge/skills/postoaklabs/ainumbers/wave-checklist/github.svg)](https://agentmods.dev/skills/postoaklabs/ainumbers/wave-checklist)
Your own site
<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/wave-checklist"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/wave-checklist/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.

agentmods 80×15 button for wave-checklist

Your own site · 80×15
<a href="https://agentmods.dev/skills/postoaklabs/ainumbers/wave-checklist"><img src="https://agentmods.dev/badge/skills/postoaklabs/ainumbers/wave-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,613 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01613
Opus 5.5 $0.00015 $0.00645
Sonnet 5.5 $0.00008 $0.00323
Haiku 4.5 $0.00004 $0.00161

Measured 3d ago against content hash 44f2608071cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wave-checklist 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 3d 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.

.claude/skills/wave-checklist/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build workflow and wave completion checklist

Moved here from repo/CLAUDE.md so it loads only when invoked. CONTRACT.md stays the SSOT.

Build Workflow

  1. Read CONTRACT.md §0-§6 (normative rules). CONTRACT-RATIONALE.md carries the same sections' explanatory prose and audit history and is optional.
  2. Generate a single .html file and place it in tools/.
  3. Validate Policy Mandate schema (CONTRACT.md §3.1), storage, and export contracts before output.
  4. Run the pre-flight checklist from CONTRACT.md §6.1.
  5. Add a card entry to the index.html tool grid (correct data-cat, data-tags, data-name).
  6. Update the category tool count in index.html cat-heading <span class="cat-n">.
  7. sitemap.xml: SKIP. It is a shared derived artifact with a single writer: derived-artifacts-regen.yml regenerates and commits it on main after every merge. A PR never edits it (two branches editing the same generated file independently caused the merge-ref skew this convention exists to prevent).

Wave Completion Checklist

BEFORE EVERY PUSH: node scripts/preflight.mjs. It runs every hard CI gate locally, in CI order (JS syntax, hash gates, index-sync, dead-link, count-drift, hub freshness, SSOT conformance, verify_repo, mfstSec). Green here means green in CI. Never push on a red preflight. The numbered items below are the individual remediation steps when a gate fails.

Mechanical enforcement: a committed pre-push hook (.githooks/pre-push) runs preflight.mjs on every push. Enable it once per clone with node scripts/setup-hooks.mjs (sets core.hooksPath = .githooks; worktrees inherit it). Emergency bypass: git push --no-verify. CI stays the real backstop.

Run after every batch of new tools/chains, before committing:

  1. JS syntax gate (BLOCKING) - node scripts/check_tools.js MUST print 0 ... syntax error and exit 0. If red, node scripts/locate_errors.js to find the break, fix, re-run. Never commit tool HTML on a red gate. (CONTRACT §6.2.) 0b. Hub freshness - chaingraph/chaingraph-hub.html is a shared derived artifact with a single writer. Do NOT run gen-chain-index.mjs and commit it in your PR; derived-artifacts-regen.yml regenerates it on main after merge. node scripts/gen-chain-index.mjs --check downgrades to advisory on a pull_request and stays blocking on main and on merge_group (the queue's CI job assembles the derived tree ephemerally into DERIVED_ROOT). A red PR-side result means main has not caught up, not that you owe a fix.
  2. Manifests - one per new tool: manifests/{number}-{slug}.manifest.json. No short-form {number}-manifest.json variants.
  3. Catalog - mcp/catalog.json, mcp/server.json, .well-known/mcp.json, llms.txt, tools.html, and index.html are shared derived artifacts with a single writer. Do NOT run or commit regen_catalog.py in your PR; derived-artifacts-regen.yml runs it on main after merge. docs/catalog.json is a copy of mcp/catalog.json written later by scripts/gen-openapi.mjs (also main-side). The freshness gate python scripts/check_index_sync.py --strict --no-color downgrades to advisory on a pull_request and stays blocking on main and on merge_group.
  4. Sitemap - sitemap.xml is a shared derived artifact with a single writer. Do NOT run or commit node scripts/regen-sitemap.mjs in your PR; derived-artifacts-regen.yml runs it on main after merge, scanning every directory in scripts/published-dirs.json (shared with scripts/verify_repo.py's check_sitemap). Gate node scripts/regen-sitemap.mjs --check downgrades to advisory on a pull_request, stays blocking on main and on merge_group. Not scripts/regen_sitemap.py (quarantined as .DEPRECATED: it knew only tools/, guides/, chaingraph/ plus seven hardcoded root pages and turned the freshness gate red).
  5. PII banners - every new tool must carry the exact CONTRACT §1.3 sentence in its rendered text. Verify: node scripts/check-pii-banner.mjs (also in preflight; a CSS/JS-only mention of the class name does not satisfy it, the check reads rendered text).
  6. Policy Mandate export - tools whose title/function involves policy, rule, mandate, routing, compliance, risk, AML, or KYC must have the Policy Mandate export button, element id ap2ExportBtn (retained legacy id, §3.1, do not rename). Check each new in-scope tool.
  7. index.html - card entry present with correct data-cat, data-tags, data-name, and updated <span class="cat-n"> count.
  8. Stat sync - mcp.html / chaingraph/chaingraph-hub.html workflow/tool-count fallbacks are shared derived artifacts with a single writer. Do NOT run --fix and commit it in your PR; derived-artifacts-regen.yml runs it on main after merge. node scripts/sync-stats.mjs (no flag) downgrades to advisory on a pull_request, stays blocking on main and on merge_group.
  9. Count-drift gate - every published count sentinel (<!--COUNT:key-->N<!--/COUNT-->, data-count="key") is a shared derived artifact with a single writer. Do NOT run --fix and commit it in your PR; derived-artifacts-regen.yml runs it on main after merge. node scripts/verify-counts.mjs --check downgrades to advisory on a pull_request, stays blocking on main and on merge_group. Never hardcode a count to make this pass: fix the sentinel or the source.

Read the full file on GitHub · 54 lines

Changes

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.

  1. 3d ago First seen · 54 lines · 38 tokens per session scan A 44f2608071cd

Subscribe to this mod's changes

wave-checklist is a skill published in the GitHub repository PostOakLabs/ainumbers (11 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,613 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.

CommitsDeterministicGit and workflowProject managementcompliancefintechmcpopenchaingraphzero-knowledge
Related

Other skills, from other repositories

gsd-quick-batch

Batch several /skill:gsd-quick-shaped tasks together — planned, dispatched, and merged as one run.

open-gsd/gsd-core · 32 tokens

gsd-pause-work

Create context handoff when pausing work mid-phase.

open-gsd/gsd-core · 16 tokens

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

engineer-bot-ops

A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.

makecindy/cindy · 57 tokens

close-task-commit-push-pr

Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.

devoxx/DevoxxGenieIDEAPlugin · 64 tokens

gait-session-tracking

GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.

automateyournetwork/netclaw · 62 tokens