Borrowing it
Nothing to install: this file belongs to npstorey/civic-ai-tools. 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/npstorey/civic-ai-tools/main/AGENTS.mdgit clone --depth 1 https://github.com/npstorey/civic-ai-toolsWrote 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/npstorey/civic-ai-tools/agents-md)<a href="https://agentmods.dev/instructions/npstorey/civic-ai-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/npstorey/civic-ai-tools/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/npstorey/civic-ai-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/npstorey/civic-ai-tools/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 | $0.02102 | $0.02102 |
| Opus 5.5 | $0.00841 | $0.00841 |
| Sonnet 5.5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade C, and why
civic-ai-tools AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Prove any install-path claim in a fresh `git clone`,** never an in-place `rm -rf node_modules`; npm 10.x runs How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
The hub repo of a four-repo project: MCP configs and setup tooling for civic open data (NYC Open Data via Socrata, Google
Data Commons), the Typed Standards Specification and its ADRs, the source of truth for shared skill guidance, and the
publish-record skill. npm workspaces (two packages, packages/civic-typed-harness and packages/civic-typed-router)
alongside Python examples. Cursor and Codex read this file natively; CLAUDE.md is a one-line bridge to it.
Boundaries
This repo is public. Strategic and relationship context — named external stakeholders, prospective collaborators, pre-meeting strategy, private outreach plans, named individuals' opinions — lives in local-only planning docs, never here. Use neutral phrasing ("an external stakeholder", "an upcoming demo") wherever output lands in this repo; if a prompt you received carries strategic context, scrub it first.
Never push to main, and never bypass a git hook or the pre-push sensitivity guard. The guard scans the added lines
of each outgoing commit, not the net diff, so a fix commit on top never clears it — rebuild the branch history.
Dependabot's PRs pass the same gates as any PR and merge only on the seat's GO, never on the bot's green alone (the two keys).
Secret hygiene (incident: civic#174, the 2026-08-22 token exposure). Never cat, head, tail, or otherwise dump
.env*, auth.json, credentials*, *.pem, *.key, or anything under ~/.ssh or ~/.aws. Two reads are permitted:
a field-scoped read by key name (grep '^VAR_NAME=' .env, or jq over non-secret fields), and a command the tool
itself exposes (publish.py --list-tokens prints prefix, scope, and expiry only). One prohibition: never
load-and-print a credentials file, even through a redaction filter — a filter applied at the wrong nesting level prints
the value it was written to hide. Publish tokens live in ~/.config/civic-ai-tools/credentials.json; --logout is
local-only, revocation is the dashboard. Setup keys belong in .env; tell a user to paste them there, never into a chat.
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 · +57 tokens per session 4ef298fc5804
- 7d ago Changed · +3 lines · +53 tokens per session b17e257bd4c6
- 27d ago Changed · +21 tokens per session cfded126920b
- 1mo ago Changed · +22 tokens per session d8b6dac0da55
- 1mo ago Changed · +1 lines · +42 tokens per session ab33c6a8bb93
- 1mo ago Changed · +1 lines · +40 tokens per session 051040481112
- 1mo ago Changed · +1 lines · +46 tokens per session bdcfc70dfe05
- 1mo ago Changed · +9 lines · +272 tokens per session 9929e988d9d8
- 1mo ago Changed 830321609058
- 2mo ago First seen · 81 lines · 1,549 tokens per session scan C 294602877f27
civic-ai-tools AGENTS.md is an instructions file published in the GitHub repository npstorey/civic-ai-tools (48 stars, last pushed yesterday), licensed MIT. It adds 2,102 tokens to every session, about $0.0084 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
civic-ai-tools AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| civic-ai-tools AGENTS.mdnpstorey/civic-ai-tools | Instructions file | 48 | yesterday | MIT | C | 2,102 | 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 |