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.
npx agentmods add instructions/mbe24/zaungast/agents-mdgit clone --depth 1 https://github.com/mbe24/zaungastWrote 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/mbe24/zaungast/agents-md)<a href="https://agentmods.dev/instructions/mbe24/zaungast/agents-md"><img src="https://agentmods.dev/badge/instructions/mbe24/zaungast/agents-md.svg" alt="Measured on agentmods" 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 | $0.00932 | $0.00932 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
zaungast 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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Policy
Execution rules for automation agents contributing to this repository. This is the single top-level source of truth.
Commit messages
For every completed task with repo changes, provide a single-line Conventional Commit message draft
in imperative language with a scope, e.g., type(scope): fix bug X in component Y. When asked to commit, use that same style for the commit itself.
Docs sync
When a change affects observable behavior, CLI usage, or workflow, ask to update the following docs:
README.md— keep usage examples and command reference current.docs/— update any affected content pages (getting-started, configuration, etc.).
If a docs page does not exist yet for new behavior, ask to create it under docs/ and register it in mkdocs.yml.
Validation — post-change
Run the same gate CI runs, then keep it green. Exact invocations live in package.json scripts and
.github/workflows/ — this section is what to check and when, not command lines to copy (they drift).
TypeScript (primary gate; mirrors CI)
The format:check → typecheck/typecheck:test → test/test:fixture/test:integration:ci chain,
after any change (especially the data layer).
Rust (packages/libzaungast-native, only when Rust source changed)
- Style/lint:
npm run check:native— wrapscargo fmt+ pedanticclippy, auto-falling back to Docker when the host can't build natively. - Behavior: the native engine must stay byte-identical to the TS reference. Run the byte-differential
via
npm run diff -- <dir|date> [--layer <name>|all](wrapsharness/run.mjs; resolves the leveldb dir, default layersstore,incr,allruns every layer); every layer must report0 differ.store+incrare the minimum — for a multi-module change, a refactor/rename, or when unsure which layer is hit, run--layer allplus the Rust unit tests (npm run test:native; pass a<dir|date>to also run theZAUNGAST_TEST_DIR-gated parity tests). Layers map to the same-named module underformat//store/.npm run verify:native -- <dir|date>chains check:native + tests +store,incr.
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.
- 4d ago First seen · 65 lines · 932 tokens per session scan A 094ad0e343ef
zaungast AGENTS.md is an instructions file published in the GitHub repository mbe24/zaungast (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 932 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
Unreal-MCP CLAUDE.md
Instructions for IvanMurzak/Unreal-MCP, covering claude.md — unreal-mcp, architecture in one screen, layout, editor vs runtime (in-game) and build / test (per leg).
calc-mcp CLAUDE.md
Claude Code instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
Noema AGENTS.md
Instructions for Fail-Safe/Noema, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
video-research-mcp AGENTS.md
Instructions for Galbaz1/video-research-mcp, covering agents.md, scope, what this is, commands and code review trigger protocol.
comfyui_mcp AGENTS.md
AGENTS.md instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.