Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/eugenepyvovarov/mcpbundler-agent-skills-marketplacenpx agentmods add skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/code-reconWrote 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/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/code-recon)<a href="https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/code-recon"><img src="https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/code-recon/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.
<a href="https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/code-recon"><img src="https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/code-recon.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.03503 |
| Opus 5 | $0.00000 | $0.01751 |
| Sonnet 5 | $0.00000 | $0.00701 |
| Haiku 4.5 | $0.00000 | $0.00350 |
Grade A, and why
code-recon 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 12d 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.
This is a copy
91% identical to zz-code-recon — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeRecon - Deep Architectural Context Building
Build comprehensive architectural understanding through ultra-granular code analysis. Designed for security auditors, code reviewers, and developers who need to rapidly understand unfamiliar codebases before diving deep.
Overview
CodeRecon is a systematic approach to codebase reconnaissance that builds layered understanding from high-level architecture down to implementation details. Inspired by Trail of Bits' audit-context-building methodology.
Why CodeRecon?
Before you can find vulnerabilities, you need to understand:
- How the system is architected
- Where data flows
- What the trust boundaries are
- Where security-critical logic lives
This skill provides a structured methodology for building that context efficiently.
The Recon Pyramid
┌─────────────┐
│ DETAILS │ ← Implementation specifics
─┼─────────────┼─
/ │ FUNCTIONS │ ← Key function analysis
/ ─┼─────────────┼─
/ │ MODULES │ ← Component relationships
/ ─┼─────────────┼─
/ │ ARCHITECTURE│ ← System structure
/ ─┼─────────────┼─
/ │ OVERVIEW │ ← High-level understanding
─────────┴─────────────┴─────────
Start broad, go deep systematically.
Phase 1: Overview Reconnaissance
1.1 Project Identification
Gather basic project information:
# Check for documentation
ls -la README* ARCHITECTURE* SECURITY* CHANGELOG* docs/
# Identify build system
ls package.json Cargo.toml go.mod pyproject.toml Makefile
# Check for tests
ls -la test* spec* *_test* __tests__/
# Identify CI/CD
ls -la .github/workflows/ .gitlab-ci.yml Jenkinsfile .circleci/
1.2 Technology Stack Detection
# Language distribution
find . -type f -name "*.py" | wc -l
find . -type f -name "*.js" -o -name "*.ts" | wc -l
find . -type f -name "*.go" | wc -l
find . -type f -name "*.rs" | wc -l
find . -type f -name "*.sol" | wc -l
# Framework indicators
grep -r "from flask" --include="*.py" | head -1
grep -r "from django" --include="*.py" | head -1
grep -r "express\|fastify" --include="*.js" | head -1
grep -r "anchor_lang" --include="*.rs" | head -1
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 483 lines · 0 tokens per session scan A 5d4bd1aa630c
code-recon is a skill published in the GitHub repository eugenepyvovarov/mcpbundler-agent-skills-marketplace (12 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,503 tokens. A static security scan graded it A with 0 findings. It is 91% identical to zz-code-recon, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
issue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…