Borrowing it
Nothing to install: this file belongs to GigleAI/cavil-loop. 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/GigleAI/cavil-loop/main/AGENTS.mdgit clone --depth 1 https://github.com/GigleAI/cavil-loopWrote 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/gigleai/cavil-loop/agents-md)<a href="https://agentmods.dev/instructions/gigleai/cavil-loop/agents-md"><img src="https://agentmods.dev/badge/instructions/gigleai/cavil-loop/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/gigleai/cavil-loop/agents-md"><img src="https://agentmods.dev/badge/instructions/gigleai/cavil-loop/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 | $0.09697 | $0.09697 |
| Opus 5.5 | $0.03879 | $0.03879 |
| Sonnet 5.5 | $0.01939 | $0.01939 |
| Haiku 4.5 | $0.00970 | $0.00970 |
Grade A, and why
cavil-loop 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 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
English · 中文
Quick context for agents (Claude Code et al.) and maintainers working in this repo. New people / agents read this first, then README.md for the external intro.
What this project is
GigleAI/cavil-loop is an Agent Skill — a feature package loaded by AI coding tools like Claude Code. It makes GitHub issue / PR comments the I/O of a local AI: a 60-second background poller on your machine finds whatever issue / PR is labeled pending/agent, spins up Claude Code locally, lets it work, push, reply, flip the label. Background in README.md.
Meta nature: this project develops itself (dogfooding). The issues / PRs of this repo run through its own workflow. On managed Linux installations, merged main revisions are published as immutable releases and activated by an atomic symlink switch on a later poll; a local checkout edit is used only after explicitly entering development mode.
Directory layout
.
├── README.md / README.zh.md ← External intro (what it is, how to use)
├── AGENTS.md / AGENTS.zh.md ← This file
├── CONTRIBUTING.md / .zh.md ← External contributor PR guide
├── SKILL.md / SKILL.zh.md ← Claude Code skill metadata (frontmatter + entry)
├── LICENSE ← MIT
├── setup.sh ← Bootstraps the daemon into a host project
├── cavil-loop.config.example ← Config template (every field commented)
├── scripts/
│ ├── _lib.sh ← Common library: config load, log, has_claude_session, run_gh
│ ├── _names.sh ← New vs pre-rename names: the one place that decides which path to use
│ ├── agent-poll.sh ← Main poller (called by systemd timer on Linux / launchd LaunchAgent on macOS)
│ ├── dispatch-new-issue.sh ← Dispatch a fresh issue
│ ├── dispatch-issue-comment.sh ← Dispatch on new issue comment
│ ├── dispatch-pr-comment.sh ← Dispatch on new PR comment
│ ├── seed-state.sh ← Initial seed of state.json
│ ├── create-worktree.sh ← Build worktree (injects worker identity)
│ ├── cleanup-issue.sh ← Post-merge cleanup (worktree / tmux / project hook)
│ ├── migrate-legacy.sh ← Move a pre-rename install to cavil-loop names (run by poll-entry.sh / setup.sh)
│ ├── _preview_adopt.sh ← Move a pre-rename preview onto the new units (shared by migrate-legacy.sh / preview-serve.sh)
│ ├── preview-resolve-conflict.sh ← Resolve a port registered in both old and new directories by different owners (by hand)
│ ├── session-log.sh ← View tmux pane history
│ ├── weekly-report/ ← Monday auto weekly report (collect / render / PDF / publish)
│ └── doc-diagrams/ ← Generator + checker for the animated SVGs in docs/images/
├── prompts/
│ ├── new-issue.template.md ← Prompt for new-issue dispatch
│ ├── issue-comment.template.md ← Prompt for new issue comment (also § A-split: split into sub-issues)
│ ├── sub-issue.template.md ← Appended for a split-out sub-issue: skip design, go straight to development
│ └── pr-comment.template.md ← Prompt for new PR comment
├── systemd/ ← Linux scheduler
│ ├── [email protected] ← User-scoped template service
│ ├── [email protected]
│ └── coding-agent-* ← Pre-rename units, kept byte for byte for old installs (see docs/operations.md)
├── launchd/ ← macOS scheduler
│ └── dev.luosky.cavil-loop.plist.template ← Generated per project by setup.sh
└── docs/
├── architecture.md / .zh.md ← Five-state label machine + session model + design FAQ
├── collaboration.md / .zh.md ← Multi-human + multi-agent workflows via label suffixes
├── persistence.md / .zh.md ← Where every artifact lives + retention + resume SOPs
├── security.md / .zh.md ← Security model + label discipline
└── operations.md / .zh.md ← Config / file layout / schedulers / troubleshooting / uninstall
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 Changed · +1 lines · +132 tokens per session fb854398ce7c
- 3d ago Changed · +2 lines · +211 tokens per session d839e808ea72
- 4d ago Changed · +1 lines · +96 tokens per session 0fbce2e6835b
- 5d ago Changed · +4 lines · +290 tokens per session f82348d47eaf
- 6d ago Changed · +2 lines · +235 tokens per session bd3544c10171
- 8d ago Changed · +4 lines · +256 tokens per session a0d05a00627a
- 10d ago Changed · +2 lines · +284 tokens per session 8d90735576b2
- 17d ago Changed · +1 lines · +311 tokens per session 6998a44e87f8
- 20d ago Changed · +98 lines · +1,627 tokens per session c4ef47995722
- 21d ago First seen · 250 lines · 6,255 tokens per session scan A 6774a6b07f59
cavil-loop AGENTS.md is an instructions file published in the GitHub repository GigleAI/cavil-loop (11 stars, last pushed yesterday), licensed MIT. It adds 9,697 tokens to every session, about $0.0388 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.