prd-map

A command that scans a code repository and records its languages, package files, entry points, folders, and development checks.

In plain words
What is it for?
Creating or refreshing a machine-readable and human-readable codebase map, and checking whether that map is outdated.
Why use it?
It gives PRD authors facts about the existing codebase instead of making them rely on memory or guesswork.

Command

Part of the prd-os plugin — 1 skill, 14 commands shipped together

Install

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.

agentmods
npx agentmods add commands/assafkip/prd-os/prd-map
Clone the repo
git clone --depth 1 https://github.com/assafkip/prd-os

Or install prd-os, the plugin that ships this one along with the rest of its 1 skill, 14 commands.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00016 $0.00421
Opus 5 $0.00008 $0.00211
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 3d ago against content hash 85511ee3f6d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prd-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 3d 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.

Origin

This is a copy

100% identical to prd-map — 0 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.

plugins/prd-os/commands/prd-map.md · 49 lines

What it actually says

Scan the current repo and write a structured codebase map to .prd-os/codebase-map.json (canonical) plus .prd-os/codebase-map.md (human-readable sibling). The map records languages, package manifests, entry points, top-level directory structure, and lint/test config. It is facts-only — no pattern distillation, no opinions.

Why this exists:

  • /prd-start produces PRDs. Without a codebase map, the author relies on memory about what already exists in the repo.
  • Codex review in /prd-review can cite the map when checking scope.
  • The map is versioned (schema_version: 1) and carries built_at + git_sha so /prd-map status can report staleness.

Security: dotenv files (.env, .env.*) have their names recorded but contents are never read. Reports/, node_modules/, .venv/, __pycache__/, and similar are skipped entirely.

Run:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_map_runner.py" build ${1:-}

If the map already exists, the runner exits non-zero. Pass --force to rebuild:

/prd-map --force

To check whether the current map is stale without rebuilding:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_map_runner.py" status

Default staleness thresholds: 30 days since last build, 50 commits ahead of git_sha at build. Override with --max-age-days or --max-commits-ahead.

Do not auto-run this inside other commands. The map is a deliberate, author-triggered artifact so PRD work stays grounded in a known snapshot rather than an ever-shifting scan.

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. 3d ago First seen · 49 lines · 16 tokens per session scan A 85511ee3f6d0

Subscribe to this mod's changes

prd-map is a command published in the GitHub repository assafkip/prd-os (10 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 421 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to prd-map, differing in 0 lines, and is treated as a copy.