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 skills add zookanalytics/gc-toolkit --skill workgit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWrote 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/zookanalytics/gc-toolkit/work)<a href="https://agentmods.dev/skills/zookanalytics/gc-toolkit/work"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/work/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.
<a href="https://agentmods.dev/skills/zookanalytics/gc-toolkit/work"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/work.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00168 | $0.03015 |
| Opus 5.5 | $0.00067 | $0.01206 |
| Sonnet 5.5 | $0.00034 | $0.00603 |
| Haiku 4.5 | $0.00017 | $0.00301 |
Grade A, and why
work 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 today.
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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work: what needs doing, and who does it
These are the ways to say that a bead needs work, who should do it, or that it
needs none. Each option says what the message means, who acts on it, and the
one writer that sends it. The writer's --help carries its flags. Doing the
work is a molecule's job, so nothing here changes a repo.
The writers are the gc-toolkit pack's own scripts.
gc <binding> scripts-dir prints their directory in the pack as gc loaded it,
so each example calls the pack's copy inside the command itself, and runs in a
fresh shell. <binding> is the name the city imports the pack under, which gc
puts in front of this skill's name: gc-toolkit in gc-toolkit.work.
gc skill list prints it in this skill's FROM column.
File new work
A new bead says that work needs doing. Filing it starts nothing: send it, make it wait, or leave it for placement.
- A dependency goes beside the bead it came from, never under it. Work
that bead waits on is a dependency, and this is the default. bd refuses a
blocksedge from a parent to its own descendant, so a child could never gate the bead it came from. Work already filed under the bead it came from stays where it is. - Work that genuinely decomposes an epic is a member of that epic. A story
or task that is part of the epic's work is filed with
--parent <that epic>, even when the epic is the bead it came from. Nothing makes the epic wait on it with ablocksedge, because containment already carries that wait. - Give it a parent only when one applies. A parent makes the bead a member
of that epic: a park on the epic holds it, and the epic's priority ranks it.
The parent of the bead it came from applies only when the new work serves the
same epic. This prints that parent, or an empty line:
"$(gc <binding> scripts-dir)/converse-parent.sh" <bead>. When no epic applies, give the bead no parent. - File it in the store of the pool that will work it. A pool reads only its
own rig's store, so a city-scoped session names the rig:
gc bd --rig <rig> create. - Send it now when intake admits it, and hold only the rest. Epics are how
the operator steers which work runs, and membership is one of four ways in
(
docs/steering.md). A bead goes to a pool now when it is a member of an epic, when it is PR-finishing work carryinganchor_bead, when it is an emergency, or when the operator routed it in a sitting, by hand or by Accept. An emergency is a red main or a broken gate, confirmed by a check that failed on the default branch's head. Critical work the operator wants run now goes through the operator's own routing. Any other bead carriesplacement=pendingin its create and no route or arm, and the operator's placement sitting places it.
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.
- today Changed · +3 lines d6083a74eee8
- yesterday First seen · 211 lines · 168 tokens per session scan A 17b97d89ab72
work is a skill published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 3,015 once invoked, about $0.0007 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 2026-10-17.
Other skills, from other repositories
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
project-awareness
Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
mission-control
Orchestrate multi-loop background operations via the Mission Control dashboard — start sessions, dispatch missions, monitor, and stop.