CommonGround: Skill for Claude Code

.agents/skills/cg-worker/SKILL.md

cg-worker is a skill for Claude Code, Codex from Intelligent-Internet/CommonGround. It costs 45 tokens per session (450 once invoked), scanned A, original, Apache-2.0.

A command-line workflow for managing CommonGround workers, which are automated jobs that claim and complete assigned work.

In plain words
What is it for?
It helps agents claim work, renew claims, append progress, finish or suspend jobs, and dispatch child workers.
Why use it?
It keeps work ownership, progress, completion, suspension, and handoffs recorded through the required worker lifecycle.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is Intelligent-Internet/CommonGround's own configuration. It tells Claude Code and Codex how to work on CommonGround 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 CommonGround configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Intelligent-Internet/CommonGround. 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/Intelligent-Internet/CommonGround/main/.agents/skills/cg-worker/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Intelligent-Internet/CommonGround

Made for: Claude Code, Codex.

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 cg-worker

README.md
[![agentmods](https://agentmods.dev/badge/skills/intelligent-internet/commonground/cg-worker/github.svg)](https://agentmods.dev/skills/intelligent-internet/commonground/cg-worker)
Your own site
<a href="https://agentmods.dev/skills/intelligent-internet/commonground/cg-worker"><img src="https://agentmods.dev/badge/skills/intelligent-internet/commonground/cg-worker/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 cg-worker

Your own site · 80×15
<a href="https://agentmods.dev/skills/intelligent-internet/commonground/cg-worker"><img src="https://agentmods.dev/badge/skills/intelligent-internet/commonground/cg-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00045 $0.00450
Opus 5.5 $0.00018 $0.00180
Sonnet 5.5 $0.00009 $0.00090
Haiku 4.5 $0.00005 $0.00045

Measured 2mo ago against content hash a44e7733be52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cg-worker 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 2mo 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.

Use `cg worker` for deterministic worker and companion lifecycle operations. Do not use `curl` for these flows when `cg worker` covers the operation.
.agents/skills/cg-worker/SKILL.md · 54 lines

What it actually says

CG Worker CLI

Use cg worker for deterministic worker and companion lifecycle operations. Do not use curl for these flows when cg worker covers the operation.

Rules

  • Use cg worker claim next to acquire work.
  • When automation needs a reusable claim token file, pass --claim-out-file.
  • --claim-file accepts either a bare claim JSON object or a full CLI envelope containing result.claim.
  • Use cg worker claim renew while the claim remains active.
  • Use cg worker claim append for progress records.
  • Use cg worker claim finish for terminal close.
  • Use cg worker claim suspend when the turn must pause for approval, orchestration, or external input.
  • Use cg worker claim dispatch-child to dispatch a child turn from an active parent claim.

Commands

Claim work and persist the claim token:

cg worker claim next \
  --project-id demo \
  --agent-id worker \
  --claim-out-file /tmp/cg-claim.json

Renew and progress:

cg worker claim renew --claim-file /tmp/cg-claim.json
cg worker claim append --claim-file /tmp/cg-claim.json --payload-file /tmp/progress.json --role progress

Finish, suspend, and child dispatch:

cg worker claim finish --claim-file /tmp/cg-claim.json --outcome succeeded --payload-file /tmp/final.json
cg worker claim suspend --claim-file /tmp/cg-claim.json --reason await_child --note "waiting on child"

cg worker claim dispatch-child \
  --claim-file /tmp/cg-claim.json \
  --requested-by worker \
  --target-agent codex \
  --payload-file /tmp/child-bootstrap.json \
  --dispatch-key child-123
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. 2mo ago First seen · 54 lines · 45 tokens per session scan A a44e7733be52

Subscribe to this mod's changes

cg-worker is a skill published in the GitHub repository Intelligent-Internet/CommonGround (153 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 450 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Related

cg-worker compared with skills from other repositories

cg-worker next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cg-workerIntelligent-Internet/CommonGroundSkill1535mo agoApache-2.0A45Claude Code, Codex
developing-genkit-toolinggenkit-ai/genkitSkill6.6kyesterdayApache-2.0A35Claude Code, Codex
emulate-seedyonatangross/orchestkitSkill299yesterdayMITA47Claude Code
architecture-patternsyonatangross/orchestkitSkill299yesterdayMITA37Claude Code
performanceyonatangross/orchestkitSkill299yesterdayMITA40Claude Code
api-designyonatangross/orchestkitSkill299yesterdayMITA47Claude Code
async-jobsyonatangross/orchestkitSkill299yesterdayMITA42Claude Code