Borrowing it
Nothing to install: this file belongs to ZoneMinder/zmNinjaNg. 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/ZoneMinder/zmNinjaNg/main/AGENTS.mdgit clone --depth 1 https://github.com/ZoneMinder/zmNinjaNgWrote 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/zoneminder/zmninjang/agents-md)<a href="https://agentmods.dev/instructions/zoneminder/zmninjang/agents-md"><img src="https://agentmods.dev/badge/instructions/zoneminder/zmninjang/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/zoneminder/zmninjang/agents-md"><img src="https://agentmods.dev/badge/instructions/zoneminder/zmninjang/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 | $0.01240 | $0.01240 |
| Opus 5.5 | $0.00496 | $0.00496 |
| Sonnet 5.5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
zmNinjaNg 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Guidelines
Portable core. This file contains no project-specific names and copies
verbatim into any project. Load order: this file, then
AGENTS.project.md (architecture contracts, project rules, verification
commands, playbooks), then the playbook it lists for your work area.
Adopting this core in another project: copy this file unchanged, then write
your own AGENTS.project.md and the gates it names. Project facts never
belong in this file.
Rule format
Every rule is a statement, a one-clause why, and a gate. A rule a script could check but names no gate is a defect here. Rules carry stable IDs by tier; docs reference IDs, never copied text.
Invariants (never simplified away)
- I1. Validate at trust boundaries: server responses, user input, IPC. Malformed input is routine, not rare.
- I2. Destructive operations need error handling and a recovery path. Lost user data cannot be patched later.
- I3. Security and accessibility are never traded for simplicity or speed. Gate: blocking accessibility and correctness lints.
Process
- P1. Create or use an issue before feature or bug work, after checking the out-of-scope ledger and any open PR for the issue (review it rather than writing a second fix); land through an issue-linked PR whose body quotes the issue's acceptance lines. Commits reference the issue; closing keywords only after the user confirms. If instructed to push directly to the default branch, do so and verify the issue timeline. Typo-level fixes and doc corrections with no behavior change need no issue.
- P2. Test first: a failing test precedes the implementation of every feature and bugfix. A test that has never failed does not demonstrate it can catch the bug. Changes an existing gate already covers fully rely on that gate instead of a bespoke new test. Gate: the proven-red CI job runs each change's tests against the pre-change code, fails when they pass, and says whether the red was an assertion or only a missing symbol.
- P3. Run the gates covering the change before every commit; run the full suite before push or PR. Never commit after a failed or unrun gate.
- P4. Read failures and fix the cause. Never blindly retry.
- P5. One logical change per conventional commit.
- P6. Verification runs direct commands. Tooling that transforms output, such as wrappers, compressors, or summarizers, is untrusted until validated once against raw output.
- P7. Finish the requested behavior. Materially different UX options need approval before choosing.
- P8. Never merge the default branch without approval.
- P10. Docs move with behavior: user docs for changed behavior, developer docs and call flows for new APIs, components, hooks, and utilities. All prose reads like a developer explaining to a colleague: no marketing language, filler, headline headings, aphorisms, or news cadence.
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 · +1 lines · +18 tokens per session 4e7c34f7e599
- 1mo ago Changed · +2 lines · +30 tokens per session fd143fef9fa0
- 2mo ago First seen · 106 lines · 1,192 tokens per session scan A cad58d14793c
zmNinjaNg AGENTS.md is an instructions file published in the GitHub repository ZoneMinder/zmNinjaNg (108 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,240 tokens to every session, about $0.0050 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.