civic.ai AGENTS.md

civic.ai AGENTS.md is an instructions file for Codex, OpenCode from audreyt/civic.ai. It costs 1,246 tokens per session, scanned A, original, CC0-1.0.

Project instructions for developing audreyt/civic.ai, a web project built with Astro and Vite+. They describe its runtime, package manager, commands, testing, and separate worker setup.

In plain words
What is it for?
Use them when installing dependencies, running checks and tests, building the site, or working on the project's Cloudflare worker.
Why use it?
They give coding agents the repository's expected commands and conventions, reducing build failures caused by using the wrong tool or runtime.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/audreyt/civic.ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/audreyt/civic.ai

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for civic.ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/audreyt/civic.ai/agents-md.svg)](https://agentmods.dev/instructions/audreyt/civic.ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/audreyt/civic.ai/agents-md"><img src="https://agentmods.dev/badge/instructions/audreyt/civic.ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,246 This file is loaded in full into every session.
When invoked 1,246 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01246 $0.01246
Opus 5 $0.00623 $0.00623
Sonnet 5 $0.00249 $0.00249
Haiku 4.5 $0.00125 $0.00125

Measured 5d ago against content hash cc21775dc40a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

civic.ai 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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build & Development

Root lifecycle: Vite+ (vp), running under its own managed Node.js runtime (pinned via package.json#devEngines.runtime, currently 22.23.1). Bun remains the configured package manager (package.json#devEngines.packageManager) and is the intentional runtime for standalone utility scripts (pangu-format.mjs, scripts/*.mjs) entered through vp run <script>, and for the isolated worker/ Cloudflare package, which keeps its own bun.lock, install, and test run, entirely separate from the root vp lifecycle — see worker:typecheck/worker:test below. Never wrap a vp lifecycle command (vp test, vp check, vp build) in Bun's own runner: it silently forces vp test's Vitest coverage-v8 provider onto Bun, which does not implement the node:inspector API coverage collection needs, and the run fails outright.

Static site generator: Astro 7

vp install              # install dependencies
vp dev                  # local Astro dev server at http://127.0.0.1:4321
vp check                # formatting check + lint + type-aware checks
vp test                 # root test suite, 100% coverage gate
vp build                # production build → ./dist/
vp run check-links      # validate built internal links in ./dist/

Verify significant changes with the relevant focused test plus vp build; before completion run the full validation chain in README/CI.

Architecture

Build pipeline: root Markdown/HTML sources + _data/* → custom markdown-it renderer and Astro layouts/components/routes → static HTML in dist/.

Content files remain top-level Markdown with YAML front matter. Do not move canonical content into src/content/; scripts/review-set.mjs, scripts/check-tw-typography.mjs, and the Vite+ staged-file hook (vp staged) rely on root *.md/tw-*.md files.

Astro source lives in src/:

  • src/lib/legacyMarkdown.ts — markdown-it, footnotes, anchors, and the CJK emphasis patch formerly in Eleventy
  • src/lib/pages.ts — typed root-content loader and URL derivation
  • src/lib/shortcodes.ts — explicit replacements for former Liquid/Nunjucks include shortcodes
  • src/components/ — shared head, navigation, footer, client scripts, Polis report, colophon
  • src/layouts/DefaultShell.astro, Default.astro, Chapter.astro, Conference.astro
  • src/pages/ — Astro routes and machine endpoints (robots.txt, llms.txt, sitemap.xml, .well-known/openclaw/SKILL.md)

Read the full file on GitHub · 67 lines

Changes

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.

  1. 5d ago First seen · 67 lines · 1,246 tokens per session scan A cc21775dc40a

Subscribe to this mod's changes

civic.ai AGENTS.md is an instructions file published in the GitHub repository audreyt/civic.ai (24 stars, last pushed today), licensed CC0-1.0. It adds 1,246 tokens to every session, about $0.0062 per session on Opus 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.

Related

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,733 tokens