Borrowing it
Nothing to install: this file belongs to alexei-led/cc-thingz. 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/alexei-led/cc-thingz/master/AGENTS.mdgit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/agents-md)<a href="https://agentmods.dev/instructions/alexei-led/cc-thingz/agents-md"><img src="https://agentmods.dev/badge/instructions/alexei-led/cc-thingz/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/alexei-led/cc-thingz/agents-md"><img src="https://agentmods.dev/badge/instructions/alexei-led/cc-thingz/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 | $0.01727 | $0.01727 |
| Opus 5.5 | $0.00691 | $0.00691 |
| Sonnet 5.5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
cc-thingz 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 10d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cc-thingz — Coding Companion
Portable skills, agents, and typed hooks for Pi, Claude Code, Codex CLI, Copilot, Cursor, and Grok. Agent Bundler (agbun) renders them from src/ into per-target packages under dist/.
Writing and communication
- Lead with the result, problem, or decision. Each sentence adds a fact, reason, or action. Omit routine narration, repeated questions, pleasantries, and empty sections.
- Use the fewest words that preserve meaning. Keep conditions, risks, compatibility limits, and genuine uncertainty explicit.
- Use one term per concept. Name the actor and the referent instead of ambiguous "this", "it", or "they".
- Replace praise and quality adjectives with evidence. Distinguish observed facts, recommendations, and unverified claims.
- For human readers, choose prose, lists, tables, or supported visuals by what explains fastest. For agent readers, use explicit operational rules, not decorative visuals.
- Use
writing-stylefor commits, PR/MR descriptions, issues, and review comments. Usedocumenting-codefor docs andwriting-skillsfor AI instructions. - These defaults apply to all generated text in the user's language. Explicit user or project requirements override them.
Build and check
make build # render dist/ and root manifests with Agent Bundler
make fmt # auto-fix Ruff, the configured JS formatter, and shfmt
make check # fail on generated drift without rewriting dist/
make ci # lint + validate + check + test + test-ts
make build,make check, andmake cineed the sandbox disabled: the uv cache at~/.cache/uvis restricted in the Claude Code sandbox.make buildneeds theagbunversion pinned in.agentbundler-version;scripts/setup/install-agbun.shinstalls it.- Commit regenerated
dist/and root manifests together with thesrc/change. - Done means
make fmtleaves no diff andmake cipasses.
Where things live
src/skills/<name>/SKILL.md— vendor-neutral skill body, withreferences/andscripts/beside it.src/agents/<name>.md— vendor-neutral role bodies.src/hooks/<name>/— typed hook assets;src/hooks/UNSUPPORTED.mdrecords per-target boundaries.src/plugins/pi/— Pi-native extension trees and the Pi compatibility runner.src/.agentbundler/packages/*.json— package membership and metadata.agentbundle.json— targets, composition, and per-targetskillPreamble.dist/— generated output; never edit it by hand.docs/— contributor docs: Agent Bundler gaps, Pi package, skill evals.tests/— pytest, Bats, Pi extension tests, andtests/skill-evals/eval suites.
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.
- 10d ago Changed · +35 tokens per session a1fa9620e2d1
- 15d ago Changed · +10 lines · +234 tokens per session 28f0d15cf70c
- 21d ago Changed · -3 tokens per session 7d8632292042
- 22d ago Changed · -42 lines · -1,065 tokens per session 2dfea69ab8bc
- 26d ago Changed · +1 lines · +42 tokens per session cac9b9eb2c56
- 1mo ago Changed · +1 lines · +58 tokens per session 9459c629f511
- 1mo ago Changed · +12 tokens per session 879b83912fc3
- 1mo ago Changed · +1 lines · +37 tokens per session c587d0c01214
- 1mo ago First seen · 121 lines · 2,377 tokens per session scan A f88b397e0b8b
cc-thingz AGENTS.md is an instructions file published in the GitHub repository alexei-led/cc-thingz (38 stars, last pushed 11d ago), licensed MIT. It adds 1,727 tokens to every session, about $0.0069 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 2026-08-30.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.