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/rdel-group/compound-knowledge-work/proof-publishernpx skills add RDEL-Group/compound-knowledge-work --skill proof-publishergit clone --depth 1 https://github.com/RDEL-Group/compound-knowledge-workWrote 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/rdel-group/compound-knowledge-work/proof-publisher)<a href="https://agentmods.dev/skills/rdel-group/compound-knowledge-work/proof-publisher"><img src="https://agentmods.dev/badge/skills/rdel-group/compound-knowledge-work/proof-publisher.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 | $0.00060 | $0.02376 |
| Opus 5 | $0.00030 | $0.01188 |
| Sonnet 5 | $0.00012 | $0.00475 |
| Haiku 4.5 | $0.00006 | $0.00238 |
Grade A, and why
proof-publisher scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: curl + python3 (both pre-installed on macOS/Linux) How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proof Publisher
Publish CKW markdown drafts to Proof — a collaborative document editor with character-level AI provenance tracking. Proof shows exactly what was written by AI vs. what was edited by humans, and gives teammates a Google-Docs-like interface for reviewing and commenting on drafts.
When to Use
- User asks to "publish to Proof", "share on Proof", "send to Proof for review"
- After
/ckw:execute-phasecompletes and drafts are ready for human review - After
/ckw:review-phasepasses and you want reviewer comments visible inline - The
/ckw:publish-proofcommand invokes this skill
Prerequisites
Check that curl is available (it should be on any macOS/Linux system):
which curl
If curl is not found:
curl is required for Proof publishing but isn't installed.
This is unusual — curl is pre-installed on macOS and most Linux distributions.
Stop here — do not attempt to publish without curl.
Proof API Reference
Proof works with both the hosted version (proofeditor.ai) and self-hosted instances. The API is identical — only the base URL changes.
| Operation | Method | Endpoint | Auth Required |
|---|---|---|---|
| Create document | POST | {base_url}/share/markdown |
None |
| Read state | GET | {base_url}/api/agent/{slug}/state |
x-share-token |
| Add comment | POST | {base_url}/api/agent/{slug}/ops |
x-share-token |
| Add suggestion | POST | {base_url}/api/agent/{slug}/ops |
x-share-token |
| Health check | GET | {base_url}/health |
None |
Usage
This skill is invoked by the /ckw:publish-proof command or conversationally. Parse the user's intent:
Single file:
Publish drafts/executive-summary.md to Proof
With review comments:
Publish drafts/executive-summary.md to Proof with review comments
Check status of existing doc:
What's the current state of the Proof doc for executive-summary?
Publishing Process
Step 1: Read Proof Configuration
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.
- 6d ago First seen · 265 lines · 60 tokens per session scan A 833a86291c1f
proof-publisher is a skill published in the GitHub repository RDEL-Group/compound-knowledge-work (9 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 2,376 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
codex-test-gen
Generate unit tests for specified functions using Codex exec.