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 rules/wshobson/agents/000-project-conventionsgit clone --depth 1 https://github.com/wshobson/agentsWrote 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/rules/wshobson/agents/000-project-conventions)<a href="https://agentmods.dev/rules/wshobson/agents/000-project-conventions"><img src="https://agentmods.dev/badge/rules/wshobson/agents/000-project-conventions.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 | $0.00322 | $0.00322 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
000-project-conventions 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.
What it actually says
claude-agents conventions
This is a multi-harness plugin marketplace. Source lives under plugins/; per-harness
artifacts (.codex/, .cursor-plugin/, .opencode/, commands/) are generated.
- Don't hand-edit anything under
.codex/,.cursor-plugin/,.opencode/, or top-levelcommands/,agents/,skills/— regenerate viamake generate HARNESS=<x>. - Python tooling:
uv(package manager),ruff(lint/format),ty(type check). Do not use pip/mypy/black. - Plugin files:
plugins/<name>/{.claude-plugin/plugin.json, agents/*.md, skills/<name>/SKILL.md, commands/*.md}. Auto-discovered. - Cursor reads
.claude/skills/and.claude/agents/directly — no separate.cursor/skills/is generated.
Never
- Never commit secrets or hardcode credentials.
- Never hand-edit generated registries (
.agents/plugins/marketplace.json,.cursor-plugin/) — plugin PRs register the plugin in.claude-plugin/marketplace.json, then runmake generate-all(see CONTRIBUTING.md). - Never run destructive git operations (force-push, reset --hard, branch -D) without explicit ask.
See docs/authoring.md for the portable-content style guide.
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 · 23 lines · 322 tokens per session scan A 3ea8c48d6f7e
000-project-conventions is a cursor rule published in the GitHub repository wshobson/agents (39,386 stars, last pushed yesterday), licensed MIT. It adds 322 tokens to every session, about $0.0016 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 2026-08-30.
Other cursor rules, from other repositories
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
execution
Repository execution and verification commands.
research-before-suggesting
Never make up features, APIs, or config options. Research before suggesting technical solutions.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
prisma
Prisma ORM best practices for type-safe database access.
implementer
Amelia — Developer agent.