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/tajd/projektor/agents-mdgit clone --depth 1 https://github.com/TAJD/projektorWrote 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/tajd/projektor/agents-md)<a href="https://agentmods.dev/instructions/tajd/projektor/agents-md"><img src="https://agentmods.dev/badge/instructions/tajd/projektor/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 | $0.06988 | $0.06988 |
| Opus 5 | $0.03494 | $0.03494 |
| Sonnet 5 | $0.01398 | $0.01398 |
| Haiku 4.5 | $0.00699 | $0.00699 |
Grade A, and why
projektor AGENTS.md scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "X-Bootstrap-Secret: localdev" http://127.0.0.1:8787/bootstrap How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and humans) working on the projektor codebase. Read this before making changes — it captures conventions that aren't obvious from the code alone.
Portable source of truth across agent tools (Claude Code, Codex, Cursor, …).
CLAUDE.mdpoints here.
What projektor is
A project management tool deployed on Cloudflare, combining AI-native design with tried-and-tested principles.
Design principles
- Fast and lightweight.
- Serverless, built on Cloudflare resources.
Implementation details:
- When implementing a feature or fixing a bug, always add a test that confirms the behaviour.
- Runtime: Hono on Cloudflare Workers
- Data: D1 (SQLite) for relational data, KV for caching (Access certs, user-by-email), R2 for file attachments
- Schema: Drizzle is the schema and primary query layer; raw
DB.prepareremains in the auth/workspace middleware hot path, the dev bootstrap, and a handful of service queries (FTS, counters) where hand-written SQL is clearer. - Monorepo: pnpm workspaces + turbo.
apps/api(the Worker),apps/web(Astro + Preact static site, served in production via CF Workers Static Assets — see below),apps/docs(the Astro docs site linked throughout this file),packages/*(db, types, plugin-sdk),plugins/* - Deploy: projektor publishes a self-contained release artifact on each
v*tag; a config-only deploy repo (e.g.projektor-deploy-example) downloads it and ships it withwrangler— no submodule, no source checkout downstream. The Worker (apps/api) and the built frontend (apps/web/dist) ship together:wrangler.tomldeclares an[assets]binding withrun_worker_first = ["/api/*", "/mcp/*", "/wiki", "/.well-known/*"], so those paths always hit the Hono Worker while every other path serves the static Astro output (per-route HTML, asset-first). The release build compilesapps/weband bundles the Worker into a singleworker.js.
Coordination model (read this first)
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.
- 3d ago First seen · 384 lines · 6,988 tokens per session scan A 986c9e89e98e
projektor AGENTS.md is an instructions file published in the GitHub repository TAJD/projektor (39 stars, last pushed 9d ago), licensed MIT. It adds 6,988 tokens to every session, about $0.0349 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ctxlayer CLAUDE.md
Instructions for stevenn/ctxlayer, covering ctxlayer — claude code briefing, what runs where, architecture pointers, how a claude session should work in this repo and conventions.
ctxlayer AGENTS.md
Instructions for stevenn/ctxlayer, covering working in this repo as an agent, golden path for any change, where things live, module rules and adding an endpoint.
nutrition-mcp CLAUDE.md
Instructions for akutishevsky/nutrition-mcp, covering claude.md, project overview, deploying, publishing to the registry and commands.
senado-br-mcp-cloudflare CLAUDE.md
Instructions for SidneyBissoli/senado-br-mcp-cloudflare, covering claude.md, project, commands, architecture and testing convention.
youtrack-mcp AGENTS.md
Instructions for VitalyOstanin/youtrack-mcp, covering repository guidelines, contributor notes, planning workflow, documentation guidelines and language policy.
rewind AGENTS.md
Instructions for pdugan20/rewind, covering rewind, work modes, development commands, agent configuration and architecture overview.