Borrowing it
Nothing to install: this file belongs to zookanalytics/gc-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zookanalytics/gc-toolkit/main/AGENTS.mdgit 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/instructions/zookanalytics/gc-toolkit/agents-md)<a href="https://agentmods.dev/instructions/zookanalytics/gc-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/zookanalytics/gc-toolkit/agents-md/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/instructions/zookanalytics/gc-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/zookanalytics/gc-toolkit/agents-md.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 | $0.00669 | $0.00669 |
| Opus 5.5 | $0.00268 | $0.00268 |
| Sonnet 5.5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
gc-toolkit AGENTS.md 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gc-toolkit
This repository is the pack every rig in the city runs, and it is also a rig of its own. What it ships as the pack, such as its skills, formulas, scripts, agent prompts and template fragments, runs in every rig (architecture.md), so a rule that binds only work on this repository is never written there. The rule goes here when every session working on the repository needs it, and otherwise into the doc or the check that owns it. Every session that works in a gc-toolkit worktree loads this file.
A docs page is a right place for such a rule, even though the polecats' standard keeps other guidance for an agent out of docs pages.
Code the deletion plan retires gets no new work
The plan is the deletion schedule in
built-once-target.md, and the
page's rule 1 links the whole files each scheduled bead retires. A problem found
in that code is not a new fix. Append it to the notes of the bead that retires
the code, so the retirement carries it. A problem that already has a bead of its
own waits on that retirement: give it an until edge to the retiring bead (the
gc-toolkit.waits skill), which closes it once the retirement lands, and send it
nowhere. A first reaction does that through its until exit. A problem that
hurts the operator now gets the smallest stopgap that stops the harm, and no new
test suite.
A change that adds operational surface shows its Gas City search
This applies to a change that adds operational surface, such as a script, a service or one of its commands, an order, a cluster of formula steps, a metadata key, a bead kind or a lifecycle state. It also applies to a change that grows existing surface with a new verb, mode or key, such as a script's new flag, a new key in its output or a new diagnostic in a doctor check. Tests, prompts, skills and a formula's prose are not surface.
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.
- 5d ago Changed · +26 lines · +355 tokens per session 7ed98d90b790
- 9d ago First seen · 24 lines · 314 tokens per session scan A 2901ae05ae10
gc-toolkit AGENTS.md is an instructions file published in the GitHub repository zookanalytics/gc-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 669 tokens to every session, about $0.0027 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 2026-10-28.
gc-toolkit AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gc-toolkit AGENTS.mdzookanalytics/gc-toolkit | Instructions file | 7 | yesterday | MIT | A | 669 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |