pm-lead-skill-patch

pm-lead-skill-patch is an agent for coding agents from ww-w-ai/bkit-claude-code. It costs 55 tokens per session (688 once invoked), scanned A, original, Apache-2.0.

A project-level patch that extends an existing product-manager agent after it finishes a PRD. It asks a skill-needs-extractor agent to find which reusable skills the planned feature may require.

In plain words
What is it for?
Use it after a product-manager workflow creates a PRD, especially through `/pdca pm`. It checks the PRD, reports covered and missing skill needs, and guides the user through creating skills for gaps after confirmation.
Why use it?
It prevents useful automation needs from being overlooked while a feature is being planned. It also gives the user a choice about creating new skills for needs that existing skills cannot cover.

Agent

Part of the bkit plugin — 19 skills, 2 commands, 35 agents, 21 hooks 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 agents/ww-w-ai/bkit-claude-code/pm-lead-skill-patch
Clone the repo
git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code

Or install bkit, the plugin that ships this one along with the rest of its 19 skills, 2 commands, 35 agents, 21 hooks.

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.

agentmods badge for pm-lead-skill-patch

README.md
[![agentmods](https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/pm-lead-skill-patch.svg)](https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/pm-lead-skill-patch)
Your own site
<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/pm-lead-skill-patch"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/pm-lead-skill-patch.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 688 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 $0.00055 $0.00688
Opus 5 $0.00028 $0.00344
Sonnet 5 $0.00011 $0.00138
Haiku 4.5 $0.00006 $0.00069

Measured 4d ago against content hash ed1fe280160c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pm-lead-skill-patch 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 4d 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.

agents/pm-lead-skill-patch.md · 95 lines

What it actually says

pm-lead Skill Needs Extension (Patch)

Purpose

기존 pm-lead 에이전트의 Phase 4 (PRD Synthesis) 완료 후, skill-needs-extractor 에이전트를 자동 호출하여 PRD에서 스킬 니즈를 추출한다.

IMPORTANT: 이 패치는 기존 bkit 플러그인 파일을 수정하지 않는다. project-local 에이전트로서 pm-lead 워크플로우에 후처리를 추가한다.

When to Activate

이 패치가 적용되는 조건:

  1. /pdca pm {feature} 완료 후 PRD 파일이 생성되었을 때
  2. docs/00-pm/{feature}.prd.md 파일이 존재할 때
  3. 사용자가 PRD 생성 결과를 확인한 후

Extension Flow

After pm-lead Phase 4 completes:

  1. Detect PRD completion:

    • Check if docs/00-pm/{feature}.prd.md was just created/updated
    • Verify it has the expected PRD structure (## Part 5: Product Requirements)
  2. Invoke skill-needs-extractor:

    • Pass the feature name
    • Pass the PRD path
  3. Present results to user:

    PRD 생성 완료: docs/00-pm/{feature}.prd.md
    
    Skill Needs Analysis:
    - N개 스킬 니즈 식별
    - N개 기존 스킬로 커버 가능
    - N개 신규 스킬 필요
    
    신규 스킬을 생성하시겠습니까? (Y/N)
    - Y: 각 GAP 스킬에 대해 /skill-create 실행
    - N: 나중에 /skill-create 으로 수동 생성
    
  4. If user confirms:

    • For each GAP skill need, prepare skill-create input
    • Guide user through /skill-create {name} for each

Integration Points

[pm-lead] Phase 1-4
    |
    v
[PRD created] docs/00-pm/{feature}.prd.md
    |
    v
[pm-lead-skill-patch] (this agent)
    |
    v
[skill-needs-extractor] agent
    |
    v
[.bkit/skill-needs.json] output
    |
    v
[User prompt] "Create N new skills?"
    |
    v
[skill-create] skill (for each GAP item)

Notes

  • This agent does NOT modify the core pm-lead agent
  • It operates as a post-processing step
  • Can be skipped if user runs /pdca plan directly without /pdca pm
  • Skill needs extraction is additive -- never removes existing skills
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. 4d ago First seen · 95 lines · 55 tokens per session scan A ed1fe280160c

Subscribe to this mod's changes

pm-lead-skill-patch is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 18d ago), licensed Apache-2.0. It adds 55 tokens to every session and 688 once invoked, about $0.0003 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.