What is pocket-agent CLAUDE.md?

A set of development instructions for PocketAgent, a lightweight asynchronous Python framework for building AI agents. It describes the project layout, constraints, modules, tools, providers, tests, documentation, and MCP integration.

Use it when changing PocketAgent agents, tools, language-model providers, orchestrators, MCP connections, tests, or English and Chinese documentation.

It gives contributors project-specific rules, reducing the risk of incompatible changes, misplaced tests, leaked secrets, or outdated documentation.

How scut-jol/pocket-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to scut-jol/pocket-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/scut-jol/pocket-agent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/scut-jol/pocket-agent

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/scut-jol/pocket-agent/claude-md/github.svg)](https://agentmods.dev/instructions/scut-jol/pocket-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/scut-jol/pocket-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/scut-jol/pocket-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/scut-jol/pocket-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/scut-jol/pocket-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 470 This file is loaded in full into every session.

When invoked 470 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00470	$0.00470
Opus 5.5	$0.00188	$0.00188
Sonnet 5.5	$0.00094	$0.00094
Haiku 4.5	$0.00047	$0.00047

Measured 2mo ago against content hash 909bebafc955, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pocket-agent CLAUDE.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 2mo 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.

CLAUDE.md · 47 lines

What it actually says

PocketAgent — Claude Code

English | 简体中文

Lightweight async-first AI Agent framework. Full docs: docs/en/ · 中文.

Layout

src/pocket_agent/ — framework core (no business logic)
examples/ — runnable demos
tests/ — unit tests only
docs/en/ · docs/zh-CN/ — architecture, features, authoritative dev constraints

Required constraints

Full spec: docs/en/development-constraints.md

Async-first: await Agent.create(...) only; no sync Agent(...).
Minimal diff: task-related files only.
Tools: @tool; state via context: Any, not globals.
Providers: implement LLMAdapter, register in create_llm_adapter(); Nous changes → tests/test_nous_parse.py.
Orchestrators: reuse StateMachine; PER event changes → sync plan_execute_review.py docstring + both docs/*/features/orchestrators.md.
MCP: via MCPManager only.
Secrets: env / .env only; never commit keys.
Tests & docs: tests in tests/; update docs/en/ and docs/zh-CN/.

Key modules

Module	Path
Agent	`src/pocket_agent/agents/base_agent.py`
@tool / ToolBox	`src/pocket_agent/tools/base_tools.py`
PlanExecuteReview	`src/pocket_agent/orchestrator/plan_execute_review.py`
FSM	`src/pocket_agent/core/fsm.py`
Nous parse	`src/pocket_agent/core/providers/nous.py`

Commands

uv sync
pytest tests/ -q

License

MIT — retain copyright notice when redistributing. See LICENSE.

Changes

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.

2mo ago First seen · 47 lines · 470 tokens per session scan A 909bebafc955

Subscribe to this mod's changes

pocket-agent CLAUDE.md is an instructions file published in the GitHub repository scut-jol/pocket-agent (3 stars, last pushed 4mo ago), licensed MIT. It adds 470 tokens to every session, about $0.0019 per session on Opus 5.5. 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.

pocket-agent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pocket-agent CLAUDE.mdscut-jol/pocket-agent	Instructions file	3	4mo ago	MIT	A	470	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode

pocket-agent: Instructions file for Claude Code