agentmods.dev

recon: Instructions file for Claude Code

CLAUDE.md

recon CLAUDE.md is an instructions file for Claude Code from cappyeo/recon. It costs 486 tokens per session, scanned A, original, MIT.

Project instructions for Recon, a code-intelligence engine that builds a map of a codebase and exposes it through MCP, a standard way for AI tools to use external capabilities.

In plain words
What is it for?
Use them when working on Recon to trace execution flows, map dependencies, assess change impact, rename code safely, or query the indexed codebase.
Why use it?
They explain how to build, index, run, and maintain the project’s code-analysis system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is cappyeo/recon's own configuration. It tells Claude Code how to work on recon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything recon configures →

not rated 5repo 6mo ago A scan 486 tokens original MIT archived
View source ↗ cappyeo/recon
Reuse

Borrowing it

Nothing to install: this file belongs to cappyeo/recon. 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/cappyeo/recon/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cappyeo/recon

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.

agentmods badge for recon CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cappyeo/recon/claude-md/github.svg)](https://agentmods.dev/instructions/cappyeo/recon/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cappyeo/recon/claude-md"><img src="https://agentmods.dev/badge/instructions/cappyeo/recon/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.

agentmods 80×15 button for recon CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cappyeo/recon/claude-md"><img src="https://agentmods.dev/badge/instructions/cappyeo/recon/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 486 This file is loaded in full into every session.
When invoked 486 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00486 $0.00486
Opus 5.5 $0.00194 $0.00194
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 2mo ago against content hash 6887b86734d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

recon 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 · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recon — Code Intelligence Engine

Project Overview

Recon is a lightweight code intelligence engine that builds a knowledge graph of codebases (13 languages via tree-sitter + TypeScript Compiler API) and exposes it via MCP (Model Context Protocol). It provides 14 tools, 3 prompts, and 5 resources for dependency mapping, blast radius analysis, safe rename, execution flow tracing, and graph queries.

Build & Run

npm install
npm run build          # TypeScript → dist/
npx recon index        # Index a codebase
npx recon serve        # Start MCP server on stdio

Architecture

  • src/analyzers/ — Go AST analysis, TypeScript compiler API analysis, cross-language API matching
  • src/graph/ — In-memory knowledge graph (KnowledgeGraph class with Map + adjacency index)
  • src/mcp/ — MCP server (stdio), tool definitions (RECON_TOOLS), tool handlers, next-step hints
  • src/storage/ — JSON serialization to .recon/ directory (graph.json + meta.json)
  • src/cli/ — Commander-based CLI with index, serve, status, clean commands

Key Patterns

  • Node IDs use namespaced prefixes: go:func:, ts:comp:, etc.
  • Incremental indexing via SHA-256 file hashing — unchanged files are skipped
  • Cross-language edges link TypeScript API calls to Go HTTP handlers
  • Every tool response includes a next-step hint guiding the agent to the logical next action

When Modifying

  • Tool definitions live in src/mcp/tools.ts — update both the definition and the handler in src/mcp/handlers.ts
  • The RECON_TOOLS array is the single source of truth for tool schemas
  • Graph types are in src/graph/types.ts — changing Node/Relationship interfaces affects serialization
  • Storage format is plain JSON — no migrations, just bump version in IndexMeta if schema changes

Do Not

  • Do not add dependencies without good reason — the project is intentionally lightweight
  • Do not modify the MCP protocol layer — use the @modelcontextprotocol/sdk as-is
  • Do not hardcode project-specific paths — Recon should work with any Go + TypeScript codebase

Read the full file on GitHub · 43 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.

  1. 2mo ago First seen · 43 lines · 486 tokens per session scan A 6887b86734d3

Subscribe to this mod's changes

recon CLAUDE.md is an instructions file published in the GitHub repository cappyeo/recon (5 stars, last pushed 6mo ago), licensed MIT. It adds 486 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.

Related

recon CLAUDE.md compared with instructions from other repositories

recon CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
recon CLAUDE.mdcappyeo/reconInstructions file56mo agoMITA486Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file280k2d agoMITA4,325Codex, OpenCode