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 skills/kimsanguine/hplan/opp-treenpx skills add kimsanguine/hplan --skill opp-treegit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/skills/kimsanguine/hplan/opp-tree)<a href="https://agentmods.dev/skills/kimsanguine/hplan/opp-tree"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/opp-tree.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 5.1 | $0.00123 | $0.03525 |
| Opus 5 | $0.00062 | $0.01762 |
| Sonnet 5 | $0.00025 | $0.00705 |
| Haiku 4.5 | $0.00012 | $0.00352 |
Grade A, and why
opp-tree 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 6d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
- 자동화 기회를 체계적으로 탐색하고 우선순위를 정하여 팀이 가장 값있는 에이전트에 투자하도록 함
- 반복빈도, 자동화가능성, 판단의존도를 기준으로 기술적 가능성과 비즈니스 가치의 균형을 맞춤
- 검증 실험 설계를 통해 구현 전에 핵심 가정(Value/Feasibility/Reliability/Ethics)을 빠르게 테스트
Trigger Gate
Use This Skill When
- 에이전트 도입을 고려 중인데 어디서부터 시작할지 결정해야 할 때
- 조직의 반복 작업, 병목 지점, 자동화 기회를 체계적으로 매핑해야 할 때
- 여러 개의 에이전트 아이디어가 있는데 어느 것을 먼저 구현할지 우선순위를 정해야 할 때
- 기술 팀과 비즈니스 팀의 의견이 갈려 "에이전트를 만들어야 하는가"를 데이터 기반으로 판단해야 할 때
Route to Other Skills When
- 선택된 기회의 가정(Value/Feasibility/Reliability/Ethics)을 깊이 있게 검증해야 할 때 →
assumptions스킬 - 최우선 기회의 기술 구현 방식(Trigger Agent vs Pipeline Agent vs Research Agent)을 결정해야 할 때 →
discover/assumptions --mode build-or-buy - 선택한 에이전트에 인간 개입 지점을 설계해야 할 때 →
hitl스킬 - Opportunity Tree를 Mermaid +
docs/OPPORTUNITY_TREE.md로 영구화하고 5/3 strong-Push 패턴으로 검증할 때 →ost(hplan plugin)
Boundary Checks
- 범위 확인: AOT는 "어떤 에이전트를 만들 것인가"를 정하는 것이지, "어떻게 만드는가"를 설명하지 않음 — 구현은
deliver/agent-setup으로 연결 - 판단 의존도 주의: 점수가 5점을 넘어가거나 판단 의존도가 높다면(4~5점) AOT 대상이 아닐 수 있음 — 그냥 Rule-based 자동화나 인간 처리가 더 나을 수 있음
Agent Opportunity Tree (AOT)
에이전트를 "만들 수 있냐"가 아니라 "만들어야 하냐"를 결정하는 프레임워크.
Teresa Torres의 Opportunity Solution Tree를 AI 에이전트 디스커버리에 맞게 재설계했습니다.
왜 에이전트에는 다른 OST가 필요한가
일반 OST는 제품 기능을 탐색할 때 씁니다.
에이전트 OST는 다릅니다. 에이전트는 자율적으로 행동하기 때문에 잘못된 기회를 선택하면 오류가 조용히 증폭됩니다.
에이전트 디스커버리에서 빠지기 쉬운 함정:
- "기술적으로 가능하니까" 만든다 → 아무도 안 씀
- "반복 작업이니까" 자동화한다 → 판단이 필요한 부분을 건드려 더 큰 문제 발생
- 에이전트 1개로 너무 많은 걸 해결하려 한다 → 실패율 급증
AOT는 이 함정을 피하기 위해 4개 레이어를 순서대로 탐색합니다.
구조 (4 레이어)
[Automation Outcome]
│
┌────┴────┐
[Opportunity] [Opportunity] ...
│
┌────┴────┐
[Agent Type] [Agent Type] ...
│
┌────┴────┐
[Experiment] [Experiment] ...
레이어 1 — Automation Outcome (자동화 목표)
단 하나의 측정 가능한 목표를 정합니다.
좋은 예: "PM이 뉴스 수집에 쓰는 시간을 주 5시간 → 0시간으로 줄인다"
나쁜 예: "업무를 AI로 자동화한다" (너무 넓음)
레이어 2 — Opportunities (기회, 문제 공간)
자동화로 해결 가능한 반복 작업, 판단 패턴, 병목 지점을 발굴합니다.
기회 프레이밍 공식:
"[누가] [어떤 상황에서] [반복적으로] [무엇을 해야 하는데] [시간/실수/비용이 든다]"
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 271 lines · 123 tokens per session scan A 76557d766e95
opp-tree is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 20d ago), licensed MIT. It adds 123 tokens to every session and 3,525 once invoked, about $0.0006 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.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).