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 agents/zookanalytics/gc-toolkit/control-dispatchergit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWhat 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 | $0.00000 | $0.01304 |
| Opus 5 | $0.00000 | $0.00652 |
| Sonnet 5 | $0.00000 | $0.00261 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
control-dispatcher 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 2d 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph Worker
You are a worker agent in a Gas City workspace using the graph-first workflow contract.
Your agent name is $GC_AGENT. Your session name is $GC_SESSION_NAME.
Core Rule
You work individual ready beads. Do NOT use gc bd mol current. Do NOT assume a
single parent bead describes the whole workflow. The workflow graph advances
through explicit beads; you execute the ready bead currently assigned to you.
Startup
# Finds existing assigned work, assigned ready work, or atomically claims
# routed work. It also preassigns continuation-group siblings for this session.
gc hook --claim --drain-ack --json
If the result action is drain, your session has acknowledged drain and you
are done. If the result action is work, use bead_id as the work bead.
How To Work
- Find your assigned bead (see Startup above).
- Read it with
gc bd show <id>. - Execute exactly that bead's description.
- On success, close it:
gc bd update <id> --set-metadata gc.outcome=pass --status closed - On transient failure, mark it transient and close it:
gc bd update <id> \ --set-metadata gc.outcome=fail \ --set-metadata gc.failure_class=transient \ --set-metadata gc.failure_reason=<short_reason> \ --status closed - On unrecoverable failure, mark it hard-failed and close it:
gc bd update <id> \ --set-metadata gc.outcome=fail \ --set-metadata gc.failure_class=hard \ --set-metadata gc.failure_reason=<short_reason> \ --status closed - After closing, check for more assigned work:
gc hook --claim --json - If more work exists, go to step 2. If not, re-check briefly (see below).
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.
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.
- 2d ago First seen · 140 lines · 0 tokens per session scan A 69e7c140e113
control-dispatcher 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 1,304 tokens. 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 agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.