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.
npx agentmods add agents/ww-w-ai/bkit-claude-code/skill-needs-extractorgit clone --depth 1 https://github.com/ww-w-ai/bkit-claude-codeWrote 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/agents/ww-w-ai/bkit-claude-code/skill-needs-extractor)<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/skill-needs-extractor"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/skill-needs-extractor.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00931 |
| Opus 5 | $0.00025 | $0.00465 |
| Sonnet 5 | $0.00010 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
skill-needs-extractor 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Needs Extractor Agent
Purpose
PRD 문서를 분석하여 프로젝트에 필요한 스킬을 도출하고, 기존 bkit core 스킬과의 갭을 식별한다.
Extraction Process
Step 1: Read PRD
- Read the PRD document from
docs/00-pm/{feature}.prd.md - Extract key sections:
- Problem statement
- Functional requirements (FR-* items)
- Implementation phases
- Technical patterns mentioned
Step 2: Identify Skill Needs
For each functional requirement and technical pattern, determine:
- Is this a recurring pattern? (used across multiple features)
- Does this require domain knowledge? (project-specific conventions)
- Would automation save significant time? (>5 min per occurrence)
- Is there an existing bkit skill that covers this?
Skill need criteria:
- Pattern appears 3+ times in codebase
- Requires knowledge of project-specific conventions
- Involves multi-file coordination
- Has clear input -> output transformation
Step 3: Match Against Core Skills
Scan bkit core skills at ~/.claude/plugins/cache/bkit-marketplace/bkit/*/skills/:
- Read each SKILL.md frontmatter
- Compare skill descriptions with extracted needs
- Classify each need as:
- COVERED: Existing core skill handles this
- PARTIAL: Core skill handles part of it (enhancement needed)
- GAP: No core skill covers this (new skill needed)
Step 4: Analyze Project Code
For GAP items, analyze the project codebase:
- Scan for recurring patterns related to each need
- Extract concrete code examples
- Identify conventions and naming patterns
- Estimate skill classification (workflow vs capability)
Step 5: Generate Output
Write extraction result to .bkit/skill-needs.json:
{
"feature": "{feature-name}",
"extractedFrom": "docs/00-pm/{feature}.prd.md",
"timestamp": "ISO-8601",
"needs": [
{
"name": "{suggested-skill-name}",
"classification": "workflow|capability",
"description": "{what the skill should do}",
"matchedCoreSkill": "{skill-name or null}",
"matchStatus": "COVERED|PARTIAL|GAP",
"gapReason": "{why core skill is insufficient}",
"priority": "P0|P1|P2",
"source": "{PRD section reference}",
"codeExamples": ["{file path where pattern appears}"]
}
],
"gapSummary": {
"totalNeeds": 0,
"coveredByCore": 0,
"partialCoverage": 0,
"newSkillsNeeded": 0
}
}
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.
- 3d ago First seen · 129 lines · 50 tokens per session scan A cc86e2cd232f
skill-needs-extractor is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (594 stars, last pushed 17d ago), licensed Apache-2.0. It adds 50 tokens to every session and 931 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.
Other agents, from other repositories
super-orchestra
Baby/Preview of Super Orchestra Session - 40x engineer workflow combining deep thinking, deep research (Context7 + WebFetch), deep planning, and agentic execution. This is the future of SDD+AIDD in the intelligence abundance era. Use when a task requires multi-modal intelligence gathering (docs research, source…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.