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/scut-jol/pocket-agent/project-constraintsgit clone --depth 1 https://github.com/scut-jol/pocket-agentWrote 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/scut-jol/pocket-agent/project-constraints)<a href="https://agentmods.dev/rules/scut-jol/pocket-agent/project-constraints"><img src="https://agentmods.dev/badge/rules/scut-jol/pocket-agent/project-constraints.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 | $0.00301 | $0.00301 |
| Opus 5 | $0.00151 | $0.00151 |
| Sonnet 5 | $0.00060 | $0.00060 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
project-constraints 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
PocketAgent Development Constraints
Authoritative spec: docs/en/development-constraints.md · 中文
Layout
src/pocket_agent/— framework core, no business logicexamples/— demostests/— tests onlydocs/en/·docs/zh-CN/— docs
Hard rules
- Use
await Agent.create(...); never syncAgent(...). - Minimal diff; no unrelated edits.
- Tools via
@tool; state viacontext: Any, not globals. - New LLM providers: implement
LLMAdapter, register increate_llm_adapter(). - Nous parse changes → update
tests/test_nous_parse.py. - MCP via
MCPManageronly; no manual subprocess spawn. - Secrets in
.env/ env vars only; never commit. - Tests in
tests/; updatedocs/en/anddocs/zh-CN/for new features.
Orchestrators
- Extend
StateMachine(core/fsm.py) for new flows. - PER UIEvent / channel changes → sync
plan_execute_review.pydocstring + both orchestrator docs.
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 · 32 lines · 301 tokens per session scan A 78425528ce63
project-constraints is a cursor rule published in the GitHub repository scut-jol/pocket-agent (3 stars, last pushed 1mo ago), licensed MIT. It adds 301 tokens to every session, about $0.0015 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.