Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspaceWrote 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/commands/yuri-semenenko/ai-engineering-workspace/codebase-map)<a href="https://agentmods.dev/commands/yuri-semenenko/ai-engineering-workspace/codebase-map"><img src="https://agentmods.dev/badge/commands/yuri-semenenko/ai-engineering-workspace/codebase-map/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/commands/yuri-semenenko/ai-engineering-workspace/codebase-map"><img src="https://agentmods.dev/badge/commands/yuri-semenenko/ai-engineering-workspace/codebase-map.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 | $0.00020 | $0.00421 |
| Opus 5.5 | $0.00008 | $0.00168 |
| Sonnet 5.5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
codebase-map 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 6d 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.
What it actually says
Codebase Map Prompt
Role: Act as a senior engineer orienting in code you do not know yet — a new repo, a subsystem you don't own, or a PR touching unfamiliar code. Produce a map, not a tour.
Context: Someone needs to become productive and safe in this codebase quickly, or to scope a change or review without having built the code themselves.
Task: Produce a short, high-signal orientation map with pointers to where each fact lives, and a "start here" shortlist.
Constraints:
- Read evidence (README, package.json, layout, existing docs); do not invent structure. Flag uncertainty rather than guessing.
- Capture: what it is, entry points, an architecture sketch, a domain glossary, key seams, risky/don't-touch areas, how to run and test, and known tradeoffs.
- Skip file-tree dumps, restating the stack from package.json, generic advice, and file-by-file summaries.
- Comprehension, not critique: note over-engineering only in passing.
- Respect Chesterton's Fence: unclear or load-bearing code is "risky", not "delete me".
- Keep it short and proportional (~80-150 lines).
Output Format:
- What it is (one paragraph)
- Entry points (start-here files)
- Architecture sketch (layers + data flow, not a file tree)
- Domain glossary (5-15 terms, one line each)
- Key seams
- Risky / don't-touch areas and invariants
- How to run and test (commands, setup, env vars)
- Known tradeoffs
- Start here: 2-4 files, plus the open questions that remain
Success Criteria:
- A newcomer can find the entry points and run the project from the map alone.
- The domain glossary uses the code's own vocabulary.
- Risky areas and invariants are called out, not silently passed over.
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.
- 6d ago First seen · 40 lines · 20 tokens per session scan A 2ece8ecd5946
codebase-map is a command published in the GitHub repository yuri-semenenko/ai-engineering-workspace (4 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 421 once invoked, about $0.0001 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 2026-10-31.
codebase-map compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codebase-mapyuri-semenenko/ai-engineering-workspace | Command | 4 | 3d ago | MIT | A | 20 | GitHub Copilot |
| spec-trace-requirementsrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| merge-conflict-analysisrjmurillo/ai-agents | Command | 49 | yesterday | MIT | A | 0 | GitHub Copilot |
| ios-buildNagarjuna2997/ios-agent-skill | Command | 40 | 8d ago | MIT | A | 19 | Claude Code |
| sdd-setupGregorBiswanger/featherspec | Command | 70 | 1mo ago | MIT | A | 27 | Claude Code |
| playwright-executekatalon-labs/true-skills | Command | 10 | 17d ago | MIT | A | 117 | GitHub Copilot |
| test-maintenancekatalon-labs/true-skills | Command | 10 | 17d ago | MIT | A | 131 | GitHub Copilot |