What is Charles-mcp AGENTS.md?

Global operating rules for an AI agent working with Charles MCP, a tool for inspecting live and saved network traffic. They define how to keep live captures, saved recordings, and reverse analyses separate.

Use them when starting traffic captures, querying recordings, replaying traffic, decoding data, or analyzing signatures.

They prevent the agent from mixing traffic sources or losing the identifiers needed to continue an analysis correctly.

How heizaheiza/Charles-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to heizaheiza/Charles-mcp. 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/heizaheiza/Charles-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/heizaheiza/Charles-mcp

Made for: Codex, OpenCode.

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/heizaheiza/charles-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/heizaheiza/charles-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/heizaheiza/charles-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/heizaheiza/charles-mcp/agents-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/heizaheiza/charles-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/heizaheiza/charles-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 819 This file is loaded in full into every session.

When invoked 819 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	$0.00819	$0.00819
Opus 5	$0.00409	$0.00409
Sonnet 5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 10d ago against content hash 0dc11145649b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Charles-mcp 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 10d 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.

AGENTS.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file defines global agent behavior rules for charles-mcp. For task-specific call sequences, see docs/agent-workflows.md. For canonical public tool contracts, see docs/contracts/tools.md.

1. Global operating model

summary first, detail on demand
live and history are separate source planes
reverse analysis extends traffic inspection into replay / decode / signature workflows
state identities must be preserved: capture_id, cursor, recording_path, live_session_id

Do not treat this server as a raw packet dump interface.

2. Identity and plane rules

Never mix source identities:
- live plane: capture_id
- history plane: recording_path
- reverse imported-analysis plane: reverse capture_id
- reverse live-analysis plane: live_session_id
Preserve and reuse returned identifiers between calls.
Do not infer cross-plane identity fallback in agent logic.
Default plane = live. When the user asks about ongoing / just-now / 现在 / 正在发生的 traffic without explicitly naming a saved recording, start with start_live_capture and stay on the live plane. Only switch to list_recordings / query_recorded_traffic / analyze_recorded_traffic when the user explicitly references a .chlsj file or 历史录包.
When unsure which plane to use, call charles_status first and follow its recommended_next_action.
Never clear the user's Charles session unless the user explicitly asks. start_live_capture defaults to adopting the user's ongoing session and preserves the traffic already captured there. Only pass reset_session=true when the user explicitly asks to clear / wipe / 清空 the session before starting a fresh capture. A wrongly-passed reset_session=true destroys the user's in-progress data and is not recoverable from this server.

3. Selection and expansion rules

Prefer group/summary tools before detail tools:
- group_capture_analysis
- query_live_capture_entries
- analyze_recorded_traffic
- reverse_query_entries
- task-oriented reverse live workflow tools
Use detail tools only for one confirmed target:
- get_traffic_entry_detail
- reverse_get_entry_detail
Do not default to full body expansion:
- keep include_full_body=false unless explicitly needed

Read the full file on GitHub · 96 lines

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.

10d ago First seen · 96 lines · 819 tokens per session scan A 0dc11145649b

Subscribe to this mod's changes

Charles-mcp AGENTS.md is an instructions file published in the GitHub repository heizaheiza/Charles-mcp (312 stars, last pushed 2mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0041 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.

ai-agent charles-proxy codex developer-tools mcp openai

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

Charles-mcp: Instructions file for Codex