A command that scans a repository and records its languages, package files, entry points, folders, and test or lint settings in a structured codebase map.

Use it before writing or reviewing a PRD, to inspect repository structure and check whether the saved map is out of date without reading environment-file contents.

It gives product requirements documents, or PRDs, factual context about the existing code instead of relying on memory or guesses.

prd-map — Command for coding agents by assafkip: A command that scans a repository and records its…

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/kipi-system/prd-map

Clone the repo

git clone --depth 1 https://github.com/assafkip/kipi-system

Or install prd-os, the plugin that ships this one along with the rest of its 2 skills, 9 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/assafkip/kipi-system/prd-map.svg)](https://agentmods.dev/commands/assafkip/kipi-system/prd-map)

Your own site

<a href="https://agentmods.dev/commands/assafkip/kipi-system/prd-map"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/prd-map.svg" alt="Measured on agentmods" height="20"></a>

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 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.

Model	Per session	Once 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 5d 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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

prd-map — 100% identical, 0 lines differ

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.

5d 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/kipi-system (108 stars, last pushed yesterday), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Planning agent-framework ai-agents ai-memory claude-code knowledge-management markdown

prd-map

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

capture

custodian

integrate

recall

add-test

query