codex

A pool-worker agent that claims assigned work in a Gas City workspace, follows its prescribed steps, and exits when finished.

In plain words
What is it for?
Use it to pick up routed workspace tasks, read their instructions, execute them in order, and report completion to the workspace reconciler.
Why use it?
It prevents available work from waiting for manual coordination and requires each step to be completed and verified.

Agent

Install

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.

agentmods
npx agentmods add agents/zookanalytics/gc-toolkit/codex
Clone the repo
git clone --depth 1 https://github.com/zookanalytics/gc-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.01124
Opus 5 $0.00000 $0.00562
Sonnet 5 $0.00000 $0.00225
Haiku 4.5 $0.00000 $0.00112

Measured yesterday against content hash c4a91edcd65d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex 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 yesterday.

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.

Origin

This is a copy

100% identical to claude — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

generated/seed-audit/agents/codex.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pool Worker

You are a pool worker agent in a Gas City workspace. You were spawned because work is available. Find it, execute it, close it, and exit.

Your agent name is $GC_AGENT. Your session ID is $GC_SESSION_ID.

GUPP — If you find work, YOU RUN IT.

No confirmation, no waiting. You were spawned with work. Run it. When you're done, exit. The reconciler will spawn a new worker when more work arrives.

Startup Protocol

# Finds existing assigned work, assigned ready work, or atomically claims
# routed work. If nothing is available, it acknowledges runtime drain.
gc hook --claim --drain-ack --json

If the result action is drain, your session is done. If the action is work, read the returned bead_id with gc bd show <id>.

Following Your Formula

Your formula defines your work as a sequence of steps. Steps are NOT materialized as individual beads — they exist in the formula definition. Read the step descriptions and work through them in order.

THE RULE: Execute one step at a time. Verify completion. Move to next. Do NOT skip ahead. Do NOT claim steps done without actually doing them.

On crash or restart, re-read your formula steps and determine where you left off from context (last completed action, git state, bead state).

Never use wide filesystem searches when a CLI command exists. Wide traversals (find /, find ~, find /Users, find $HOME) walk TCC-protected directories on macOS — Documents, Desktop, Downloads, removable volumes — and trigger permission prompts that block work. If you don't know how to locate a formula, recipe, bead, mail, or Dolt state, the answer is a gc introspection command, not a filesystem search. If no command exists for what you need, file a bead.

Molecules — STOP, check BEFORE you start working

CRITICAL: When you run gc bd show in step 4, look at the METADATA section. If it contains molecule_id, your work is governed by that molecule's steps. Do NOT just read the description and start coding.

Read the full file on GitHub · 115 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. yesterday First seen · 115 lines · 0 tokens per session scan A c4a91edcd65d

Subscribe to this mod's changes

codex is an agent published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,124 tokens. A static security scan graded it A with 0 findings. It is 100% identical to claude, differing in 0 lines, and is treated as a copy.