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 skills add kimsanguine/hplan --skill sprintgit 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/sprint)<a href="https://agentmods.dev/skills/kimsanguine/hplan/sprint"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/sprint.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 | $0.00069 | $0.05247 |
| Opus 5 | $0.00034 | $0.02624 |
| Sonnet 5 | $0.00014 | $0.01049 |
| Haiku 4.5 | $0.00007 | $0.00525 |
Grade A, and why
sprint 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 8d 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 — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
네 스텝을 단일 인터페이스로 통합한다:
| step | 책임 | LLM | 출력 |
|---|---|---|---|
--step plan |
PRD → WBS 분해, complexity 1-5 분류, velocity lookup → .track/predicted.json |
✅ WBS/분류만, 수치 예측 ❌ | predicted.json |
--step init |
.track/ 생성, probe hook 등록, 추적 초기화 |
❌ 결정론 | .track/actual_log.jsonl + hook |
--step status |
jsonl 블로커 패턴 결정론 스캔 + 이벤트 트리거 현황 보고 | ✅ 자연어 렌더링만 | 진행 보고 |
--step retro |
완료 후 실측 vs 예측 deviation 분석 + TK 추출 | ✅ 분류/자연어 | retro report |
--step codebase-status |
코드베이스 능동 탐색 → PM 현황 보고 | ✅ 산문 합성만 | codebase-report.md |
기본값:
--step plan— 첫 진입은 항상 계획부터.
Rule 5 준수 경계
| 작업 | LLM 사용 | 근거 |
|---|---|---|
| WBS 분해 | ✅ 분류 | 텍스트 → sub-task 분류 |
| complexity 1-5 분류 | ✅ 분류 | description 텍스트 기반 분류 허용 |
| loc/tokens/minutes 수치 예측 | ❌ lookup 전용 | baseline percentile 직접 인용, hallucination 방지 |
| 블로커 패턴 감지 | ❌ 결정론 | 정규식·카운터·임계치 비교 |
| 7종 트리거 검출 | ❌ 결정론 | 카운터·임계치 비교 |
.track/current_task 기록 |
❌ 결정론 | echo T-XXX > .track/current_task (LLM 아님) |
| 자연어 보고 문구 생성 | ✅ | Rule 5 허용: 자연어 생성 |
Trigger Gate
Use This Skill When
- PRD 받자마자 WBS + 예측치 lock →
--step plan - plan 완료 후 추적 환경 세팅 →
--step init - "지금 어디까지 왔어?" / "블로커 있어?" →
--step status - 스프린트 완료 후 회고 + TK 추출 →
--step retro - estimate vs actual deviation 50% 초과 →
--step plan재실행 - "지금 코드 어디까지 됐어?" / "probe 없는 환경에서 현황 보고" →
--step codebase-status
Route to Other Skills When
- 비용 시뮬레이션 (lognormal) →
discover/cost-sim - WBS 30 task 초과 →
deliver/conductor로 태스크 순차 실행 - UI 디자인 확인 →
deliver/ui-validate - 주간 운영 회고 →
operate/ops-review
Boundary Checks
- PRD vague (Section 6 누락) → fail loud, PRD 보강 요청
- baseline 부재 → conservative fallback (모든 task complexity 5 추정치 × 1.5) + warning
.track/actual_log.jsonl부재 시 status → "init 먼저" fail loud
Inputs
| 입력 | 출처 | 처리 |
|---|---|---|
--step |
$ARGUMENTS |
plan/init/status/retro/codebase-status 분기 |
| target | $ARGUMENTS (step 이후 나머지) |
PRD 경로 또는 feature 설명 |
profiles/<op>/velocity/baseline.jsonl |
velocity-baseline 또는 plan step | estimate lookup 기준 |
.track/predicted.json |
plan step 출력 | status/retro 비교 기준 |
.track/actual_log.jsonl |
init + probe hook | status/retro 실측 데이터 |
What ships with it
2 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.
- 8d ago First seen · 476 lines · 69 tokens per session scan A 5059f36dc163
sprint is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 69 tokens to every session and 5,247 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 2026-08-31.
Other skills, from other repositories
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
req-analyze
A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.
recap-ask
Interactive Q&A over an existing recap document. Use when: user wants to ask follow-up questions about a briefing-recap- .md produced by /recap-doc, with recap-bounded context + out-of-scope redirect + optional promote-to-request. Not for: generating a new recap (use /recap-doc), general project Q&A (use /ask), code…
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…
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).
jira
Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).