scout

/scout — External Link Analysis

Analyze an external URL (tech blog, tool, library, methodology) to evaluate its fit with the oh-my-customcodex project and auto-create a GitHub issue with a structured verdict.

Sensitive-Path Delegation

Sensitive-path compatibility note: if this skill delegates work that touches .claude/**, .claude/outputs/**, templates/.claude/**, or read-only measurements of those paths, keep .codex/** edits on the normal Codex path. On Claude Code v2.1.121+ with bypassPermissions, direct writes to .claude/skills/, .claude/agents/, and .claude/commands/ are allowed; on v2.1.126+ that extends to broader protected paths. Only use /tmp/{skill}-{timestamp}.md as a legacy fallback when the target runtime is older or still prompts.

Usage

/scout <url>
/scout https://news.hada.io/topic?id=27673
/scout https://github.com/user/repo

Verdict Taxonomy

Pre-flight Guards

Pre-flight Execution Checklist (MANDATORY before Phase 1)

Both guards MUST be executed before entering Phase 1. Skipping either guard is a workflow violation.

• Guard 1: URL Validity check passed (abort if invalid)
• Guard 2: Duplicate Scout check passed (warn and confirm if duplicate found)

Proceed to Phase 1 only after both checkboxes are satisfied.

Guard 1: URL Validity (GATE)

Before any work, validate the URL:

# Check URL is syntactically valid
echo "$URL" | grep -qE '^https?://'

If invalid: [Pre-flight] GATE: Invalid or unreachable URL. Please check and retry. — abort.

Guard 2: Duplicate Scout (WARN)

Search existing GitHub issues for prior scout reports on the same URL domain:

DOMAIN=$(echo "$URL" | sed 's|https\?://||' | cut -d'/' -f1)
gh issue list --state all --label "scout:internalize,scout:integrate,scout:skip" \
  --json number,title,body --jq ".[] | select(.body | contains(\"$DOMAIN\"))" 2>/dev/null

If found: [Pre-flight] WARN: Similar URL already scouted in issue #N. Proceed anyway? [Y/n]

Why mandatory? Guard 2 생략으로 인해 동일 도메인 중복 scout 이슈가 생성된 사례 발생. 중복 triage 낭비를 방지하기 위해 Pre-flight 체크리스트로 승격.

Display Format

Before execution, show the plan:

[Scout] {url}
├── Phase 1: 콘텐츠 수집 및 요약
├── Phase 2: 프로젝트 철학 로드
├── Phase 3: 적합성 분석 (frontier/medium)
└── Phase 4: 이슈 생성

예상: ~1분 | 비용: ~$0.5-1.5
실행하시겠습니까? [Y/n]

암묵 승인 시 필수: "되면 /scout으로 보고", "실행해줘" 등 묵시적 승인인 경우에도 위 plan 요약을 반드시 1줄 이상 표시한 뒤 진행한다. plan 표시 없이 바로 Phase 1으로 진입하지 않는다.

Workflow

Phase 1: Fetch & Summarize

1. WebFetch(url) — retrieve page content
2. Extract core information:
   • Title and purpose
   • Key technology / methodology
   • Approach and principles
3. If fetch fails — report error, abort

External quantitative-fact source tagging (#1466): WebFetch가 산출한 구체적 정량 주장(benchmark 수치, table 값, metric)은 이슈 본문에 WebFetch-derived (unverified)로 태깅한다 — 검증된 사실로 제시하지 않는다. WebFetch 캐시/요약은 독립 ground-truth가 아니므로, load-bearing 수치는 primary PDF/원문으로 1회 검증하거나 명시적으로 unverified로 표기한다. (R020 Read-Before-Characterize, R023 Verifier Ground-Truth)

Phase 2: Load Project Philosophy

1. Read(AGENTS.md) — extract architecture philosophy:
   • Compilation metaphor (source -> build -> artifact)
   • Separation of concerns (R006)
   • Dynamic agent creation ("no expert? create one")
   • Skill/agent/guide/rule structure
2. Read(README.md) — extract project overview and component inventory
3. Glob(.codex/skills/*/SKILL.md) — list existing skills for overlap detection

Phase 3: Fit Analysis

Spawn 1 frontier/medium agent with the following analysis prompt.

Claude compatibility Agent calls only (R010 “Delegated Permission Ownership”): Pass mode: "bypassPermissions" when the active Claude session uses bypass permissions. Native Codex spawn_agent has no mode parameter; use the installed agent_type and active Codex runtime permissions instead.

Inputs:

• Fetched content summary (Phase 1)
• Project philosophy context (Phase 2)
• Existing skill list (Phase 2)

Analysis dimensions:

Agent prompt template:

You are a project fit analyst. Given:

1. External content summary:
{phase1_summary}

2. Project philosophy:
{phase2_philosophy}

3. Existing skills ({skill_count} total):
{skill_list}

Analyze the external content against the project philosophy across 4 dimensions:
- Philosophy alignment
- Technical fit (overlap with existing skills?)
- Integration effort (XS/S/M/L)
- Value proposition

Return a structured verdict:
- verdict: INTERNALIZE | INTEGRATE | SKIP
- priority: P1 | P2 | P3
- rationale: 2-3 sentences
- philosophy_table: criterion/fit/rationale for each dimension
- recommendation: specific integration plan or skip reason
- next_steps: 2-3 actionable items
- IMPORTANT: Write all analysis output in Korean. Technical terms, code references, label names, and skill/agent names stay in English.
- escalation: true/false (INTERNALIZE + M/L effort = true)

Output: Structured verdict with rationale.

Phase 4: Issue Creation

NOTE: Phase 4 is normally handled by the orchestrator with gh issue create. If issue creation is delegated through a Claude compatibility Agent call, pass mode: "bypassPermissions" only when that Claude session uses bypass permissions. Native Codex spawn_agent never accepts mode.

1. Ensure scout labels exist (defensive, idempotent):

gh label create "scout:internalize" --color "0E8A16" --description "Scout: should be internalized" 2>/dev/null || true
gh label create "scout:integrate" --color "1D76DB" --description "Scout: keep as external" 2>/dev/null || true
gh label create "scout:skip" --color "D4C5F9" --description "Scout: skip" 2>/dev/null || true

2. Create GitHub issue:

gh issue create \
  --title "[scout:{verdict}] {content_title}" \
  --label "scout:{verdict},P{n}" \
  --body "{issue_body}"

3. If verdict is SKIP: auto-close the issue:

gh issue close {number} -c "Auto-closed: scout verdict is SKIP"

Issue Body Template

## Scout 리포트: {title}

**출처**: {url}
**판정**: {INTERNALIZE / INTEGRATE / SKIP}
**우선순위**: {P1 / P2 / P3}

## 요약
{외부 콘텐츠에 대한 2-3문장 요약}

## 프로젝트 철학 정합성
| 기준 | 적합 | 근거 |
|------|------|------|
| Compilation metaphor | {check/cross} | {설명} |
| Separation of concerns (R006) | {check/cross} | {설명} |
| Dynamic agent creation | {check/cross} | {설명} |
| 기존 스킬 중복 | {check/cross} | {중복 스킬 목록} |

## 권장 사항
{구체적 통합 계획 — 어떤 skill/agent/guide를 생성할지, 또는 건너뛰는 이유}

## 다음 단계
- [ ] {후속 조치 1}
- [ ] {후속 조치 2}

---
`/scout`에 의해 생성됨

Escalation

When verdict is INTERNALIZE and integration effort is M or L:

[Advisory] 심층 분석 권장.
└── 실행 검토: /research {url}

Result Display

[Scout 완료] {title}
├── 판정: {INTERNALIZE / INTEGRATE / SKIP}
├── 우선순위: {P1 / P2 / P3}
├── 이슈: #{number}
└── 에스컬레이션: {/research 권장 | 없음}

Capability Routing

Integration

When NOT to Use

Differences from /research