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/evilfreelancer/zaezd/agents-mdgit clone --depth 1 https://github.com/EvilFreelancer/zaezdWhat 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 | $0.01542 | $0.01542 |
| Opus 5 | $0.00771 | $0.00771 |
| Sonnet 5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
zaezd 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 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.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zaezd - agent brief
Trip engine that starts from a reason to travel. A person does not know where to go, they know why. The first vertical is IT conferences: the event catalogue (confcal MCP) says where and when, Tutu MCP supplies transport and lodging, and a deterministic composer turns both into at most three explainable packages on one screen.
The product specification lives in specs/ and is authoritative. Read
specs/README.md first; it indexes all ten documents and names the three
things that are never cut: the return leg, the deterministic date algorithm, and honest
checkout link labels.
State of the repository
All five layers are written, specified and deployed: the pure core, the confcal and Tutu
clients, the three optional enrichments, the orchestrator, the trip board and the three MCP
tools with the ui:// widget. It ships as a container and runs behind whatever reverse proxy
a deployment happens to have; npm run verify covers all of it offline against fixtures/.
ideas/ holds the reconnaissance the specs were built from. It ships with the public
repository as history, not as product code, and nothing under src/ may import from it.
research/ holds raw probes and review transcripts and stays out of git.
Commands
npm install # once
npm start # the server, ZAEZD_MODE=live or replay
npm run bdd # executable Gherkin specifications (features/)
npm test # unit tests (tests/)
npm run typecheck # tsc over the Node tree and the browser tree
npm run lint # eslint
npm run rules:sync # regenerate .cursor/rules from .claude/rules
npm run docs:check # every command the documentation names really exists
npm run build # compile to dist/ and copy static assets
npm run verify # all of the above except build, the gate before calling anything done
Runtime dependencies are added as the layer that needs them is built: zod with
src/sources/normalize.ts, @modelcontextprotocol/sdk with the clients,
@modelcontextprotocol/ext-apps with the ui:// resource. Leaflet and the Kite token
extract are vendored under src/web/public/vendor/ with their licences, not installed.
Unused dependencies are a scored defect here.
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 First seen · 131 lines · 1,542 tokens per session scan A 4166da4667ee
zaezd AGENTS.md is an instructions file published in the GitHub repository EvilFreelancer/zaezd (1 stars, last pushed 13d ago), licensed MIT. It adds 1,542 tokens to every session, about $0.0077 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
wanderlog-mcp CLAUDE.md
Instructions for shaikhspeare/wanderlog-mcp, covering wanderdog — agent instructions, read before making changes, keep the kanban in sync, invariants (from docs/architecture.md — do not violate) and dev commands.
mTarsier AGENTS.md
Instructions for mcp360/mTarsier, covering mtarsier — agent guide, project overview, key paths, architecture and frontend conventions.
metmuseum-mcp CLAUDE.md
Instructions for mikechao/metmuseum-mcp, covering claude.md, project overview, development commands, install dependencies (requires pnpm) and type checking.
mTarsier CLAUDE.md
Instructions for mcp360/mTarsier, covering mtarsier — claude code instructions and quick rules.
metmuseum-mcp AGENTS.md
Instructions for mikechao/metmuseum-mcp, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
brick-mcp-app CLAUDE.md
Instructions for dend/brick-mcp-app, covering brick builder mcp app, important rules, specs, tech stack and key commands.