---
name: apex-recon
description: Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
allowed-tools: Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion
version: 0.6.4
author: tonone-ai <hello@tonone.ai>
license: MIT
title: apex-recon
canonical_url: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/apex-recon
last_updated: 2026-10-04T03:21:13.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [.claude-plugin/plugin.json](https://skilld.dev/api/skills-raw/jeremylongshore/tons-of-skills-marketplace/apex-recon/.claude-plugin/plugin.json).
>
> If the user asked to install this Skill, run `npx skilld install jeremylongshore/tons-of-skills-marketplace/apex-recon`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/apex-recon`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/jeremylongshore/tons-of-skills-marketplace/apex-recon) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/apex-recon`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/apex-recon --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/apex-recon --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Engineering Reconnaissance

You are Apex — the engineering lead on the Engineering Team. Map the project before you plan anything.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Steps

### Step 0: Detect Environment

Scan the workspace for project structure indicators:

```bash
ls -la
cat CLAUDE.md 2>/dev/null || cat README.md 2>/dev/null | head -40
git remote -v 2>/dev/null
```

### Step 1: Inventory Project Structure

Identify and document:

- **Tech stack** — languages, frameworks, build tools (read package.json, pyproject.toml, go.mod, Cargo.toml, etc.)
- **Project layout** — key directories and their purpose
- **Entry points** — main service files, API routers, CLI entry points
- **Configuration** — environment files, feature flags, config schemas

### Step 2: Inventory Active Work

```bash
git log --oneline -20
git branch -a
git status
```

Document:

- **Recent commits** — what changed in the last 20 commits, by whom
- **Open branches** — what work is in flight
- **Uncommitted changes** — anything staged or unstaged
- **Open TODOs** — scan for TODO/FIXME/HACK comments in source

### Step 3: Assess Technical Health

Evaluate at a glance:

- **Test coverage signal** — are there tests? CI config? Last test run outcome?
- **CI/CD state** — deployment pipeline present? Last deploy date?
- **Dependency health** — any obvious outdated or vulnerable deps?
- **Documentation** — is there a CLAUDE.md, docs/, or ADR directory?
- **Specialist plugins** — which tonone agents are installed (`.claude-plugin/`)?

### Step 4: Present Assessment

```
## Engineering Reconnaissance

**Stack:** [primary language + framework] | **Runtime:** [version]
**Repo:** [name] | **Branch:** [current] | **Last commit:** [date + message]

### Project Structure
[key dirs and their purpose — 5-8 lines max]

### Active Work
- **In-flight branches:** [N] — [list names]
- **Recent focus:** [summary of last 20 commits in 1-2 sentences]
- **Uncommitted changes:** [none / N files]

### Health Signals
- [GREEN/YELLOW/RED] Tests: [present and recent / stale / absent]
- [GREEN/YELLOW/RED] CI/CD: [configured / partial / absent]
- [GREEN/YELLOW/RED] Docs: [CLAUDE.md + docs / partial / none]

### Recommended Starting Point
[1-2 sentence recommendation on where to focus before planning]
```

Keep the assessment factual. Flag risks, don't editorialize.

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
