extract-issues

A workflow that reads a note and turns possible work items into proposed issues, each marked with an AI confidence level.

In plain words
What is it for?
Use it to find action items, create issue titles and descriptions, link them to source blocks, and suggest labels and priorities.
Why use it?
It removes the need to manually spot every task, bug, or feature request hidden in brainstorming notes.

Skill for Claude CodeCodex

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 skills/pilotspace/pilot-space/extract-issues
Any agent
npx skills add pilotspace/pilot-space --skill extract-issues
Clone the repo
git clone --depth 1 https://github.com/pilotspace/pilot-space

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,335 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 $0.00014 $0.01335
Opus 5 $0.00007 $0.00668
Sonnet 5 $0.00003 $0.00267
Haiku 4.5 $0.00001 $0.00134

Measured 2d ago against content hash 3baa85ed4fd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

extract-issues 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.

backend/src/pilot_space/ai/templates/skills/extract-issues/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Issues Skill

Extract actionable issues from note canvas content using semantic analysis and confidence scoring.

Quick Start

Use this skill when:

  • User finishes brainstorming in note canvas
  • AI detects potential work items in note content
  • User explicitly requests issue extraction (/extract-issues)

Example:

User writes in note:
"We need to implement JWT authentication and add rate limiting
to the API. Also fix the login bug where users can't log in with email."

AI extracts:
- Issue 1: "Implement JWT authentication" (RECOMMENDED)
- Issue 2: "Add API rate limiting" (RECOMMENDED)
- Issue 3: "Fix email login bug" (RECOMMENDED - explicit bug mention)

Workflow

  1. Analyze Note Content

    • Parse note blocks (paragraphs, lists, headings)
    • Identify action items using verb patterns (implement, fix, add, create)
    • Detect explicit issue references ("bug", "feature", "task")
  2. Extract Candidate Issues

    • For each potential issue:
      • Extract name (concise title, ≤100 chars)
      • Extract description (context from surrounding text)
      • Identify block_id for source linking
      • Detect labels from keywords (backend, frontend, security, etc.)
      • Infer priority from urgency markers (critical, urgent, nice-to-have)
  3. Score Confidence

    • RECOMMENDED: Clear action item with explicit verb and context
      • Example: "Implement user authentication with JWT tokens"
    • DEFAULT: Implied action from discussion context
      • Example: "Authentication should use JWT" (implies implementation)
    • ALTERNATIVE: Possible interpretation, needs clarification
      • Example: "Maybe we should consider caching?" (tentative)
  4. Return Structured Output

    • JSON array of issues with confidence tags
    • Preserve source block links
    • Include rationale for each confidence score

Output Format

{
  "issues": [
    {
      "name": "Implement JWT authentication",
      "description": "Add JWT-based authentication with refresh tokens to replace session cookies",
      "confidence": "RECOMMENDED",
      "source_block_id": "block-abc123",
      "labels": ["backend", "security"],
      "priority": "high",
      "rationale": "Clear implementation task with specific requirements (JWT, refresh tokens)"
    },
    {
      "name": "Add API rate limiting",
      "description": "Implement rate limiting middleware to prevent API abuse",
      "confidence": "RECOMMENDED",
      "source_block_id": "block-def456",
      "labels": ["backend", "infrastructure"],
      "priority": "medium",
      "rationale": "Explicit action item, standard security practice"
    },
    {
      "name": "Fix email login bug",
      "description": "Users cannot log in using email addresses, investigate validation logic",
      "confidence": "RECOMMENDED",
      "source_block_id": "block-ghi789",
      "labels": ["backend", "bug"],
      "priority": "critical",
      "rationale": "Explicit bug mention, blocks user access"
    }
  ],
  "summary": "Extracted 3 issues from note content",
  "total_blocks_analyzed": 8
}

Read the full file on GitHub · 194 lines

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 · 194 lines · 14 tokens per session scan A 3baa85ed4fd4

Subscribe to this mod's changes

extract-issues is a skill published in the GitHub repository pilotspace/pilot-space (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,335 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.