prp

A command that turns an approved PRD, or product requirements document, into a Product Requirements Prompt for an engineering handoff.

In plain words
What is it for?
Use it to generate and save a handoff document for engineers after product requirements are approved.
Why use it?
It provides a structured bridge from agreed product requirements to technical implementation work. It also checks that the source PRD is approved and validates the result.

Command for Claude Code

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/pierry/harness-kit/prp
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

Made for: Claude Code.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 867 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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00867
Opus 5 $0.00013 $0.00434
Sonnet 5 $0.00005 $0.00173
Haiku 4.5 $0.00003 $0.00087

Measured 2d ago against content hash 2ac5d1b7913b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prp 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 2d 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.

.claude/commands/product-manager/prp.md · 54 lines

What it actually says

Generate PRP. Follow .claude/agents/product-manager/guides/pipeline.md for retry, approval, publish, and .claude/shared/pipeline-pattern.md for inputs (resolve-mark-proceed) and eval (adversarial).

Print header card before drafting and footer card after gates run. Format: .claude/scripts/stage-card.md.

Source PRD: user passes path, use it. Else pick most recent in .claude/runtime/outputs/pm/prd/. None found, abort. Tell user to run /product-manager:prd first. .claude/runtime/hooks/product-manager/pre-prp-check.sh blocks if PRD lacks approved marker.

Compute feature_id from source PRD filename (basename without .md). Save PRP to .claude/runtime/outputs/pm/prp/{feature_id}.md so it matches.

Before generating, write the phase start marker by running this script. Do NOT inline date/printf (command-substitution + redirect always trips the permission prompt):

.claude/scripts/marker.sh start .claude/runtime/outputs/pm/.markers/{feature_id}.prp-generate.start

Read:

  • source PRD
  • .claude/runtime/outputs/intake/{feature_id}.md (for resolved repos, squad, metric)
  • .claude/agents/product-manager/guides/prp-guidelines.md
  • .claude/agents/product-manager/guides/writing-style.md
  • .claude/agents/product-manager/guides/templates/prp.md
  • .claude/agents/product-manager/guides/pipeline.md
  • .claude/agents/product-manager/guides/examples/good-prp-example.md

Explore target repos. Resolve repo paths without asking (resolve-mark-proceed): take them from the intake artifact's repos frontmatter, else context-library/repos.md, else auto-detect from the current working directory and git remotes. Only if none of these yield a path, mark NOT FOUND - NEEDS REVIEW: target repo and proceed. Use Grep and Read to map files. Capture file:line. Never invent paths.

Save to .claude/runtime/outputs/pm/prp/{feature_id}.md.

Sensors: run deterministically via the committed runner. Do NOT improvise inline grep/for loops:

.claude/runtime/scripts/product-manager/run-sensors.sh .claude/runtime/outputs/pm/prp/{feature_id}.md .claude/agents/product-manager/sensors/prp-structure.md .claude/agents/product-manager/sensors/prp-context-quality.md .claude/agents/product-manager/sensors/prp-links.md

Exit 0 = all pass; exit 1 = a sensor blocked (the runner prints which). Read a sensor spec with the Read tool only to explain a failure; never cat it in a loop.

Evals: .claude/agents/product-manager/evals/prp-quality.md, .claude/agents/product-manager/evals/prp-context-readiness.md.

Run the evals adversarially: dispatch a fresh evaluator via the Task tool (subagent_type: general-purpose) that did not author this PRP. Hand it only the artifact path and the two rubric paths; it scores against the rubrics and reports weighted totals plus the low-scoring dimensions. Below threshold (8.0) retries per pipeline.md, regenerating only the flagged dimensions.

After save, reply with this exact shape (name actual sensors/evals/guides that ran):

PRP saved at {path}.
  sensors: prp-structure ok, prp-context-quality ok, prp-links ok
  eval:    prp-quality {N}/10, prp-context-readiness {N}/10
  guides:  prp-guidelines.md, writing-style.md, templates/prp.md
  refs:    prd/{feature_id}.md, {target repo paths probed}
  next:    /sse:plan (ready for handoff)
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. 2d ago First seen · 54 lines · 25 tokens per session scan A 2ac5d1b7913b

Subscribe to this mod's changes

prp is a command published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 867 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 2026-08-31.