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 Dannykkh/skill-olympus --skill okrgit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/okr)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/okr"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/okr.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 | $0.00059 | $0.01500 |
| Opus 5 | $0.00030 | $0.00750 |
| Sonnet 5 | $0.00012 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
okr 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 4d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKR — 목표와 핵심결과
분기별 Objectives(목표)와 Key Results(핵심결과)를 설정하고 추적합니다.
Quick Start
/okr # 새 OKR 설정
/okr review # 기존 OKR 진행률 확인
/okr retro # 분기 회고
공식 호출명: /okr (별칭: 목표 설정, 분기 계획)
CRITICAL: First Actions
1. Print Intro
OKR — 목표와 핵심결과 설정
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
모드: Set (설정) / Review (점검) / Retro (회고)
2. 모드 결정
| 모드 | 조건 | 동작 |
|---|---|---|
| Set | docs/okr/ 없거나 새 분기 |
새 OKR 설정 |
| Review | docs/okr/current.md 있음 |
진행률 업데이트 |
| Retro | 분기 종료 시 | 달성률 평가 + 회고 |
Mode: Set (새 OKR 설정)
Step 1: 컨텍스트 수집
현재 CLI의 질문 방식으로 확인:
question: "이번 분기(Q?)의 핵심 목표가 뭔가요?"
header: "OKR 설정"
기존 산출물 참조 (있으면, archive/ 경로 제외):
docs/hermes/*.md→ 사업 분석에서 목표 도출docs/plan/*/spec.md→ 기술 계획에서 목표 도출
Step 2: Objectives 설정
규칙:
- 2~4개 Objective (너무 많으면 집중력 분산)
- 정성적, 영감을 주는 문장
- "무엇을 달성할 것인가" (측정 방법은 KR에서)
O1: {영감을 주는 목표}
O2: {영감을 주는 목표}
O3: {영감을 주는 목표}
Step 3: Key Results 설정
각 Objective에 2~4개 Key Result:
규칙:
- 정량적, 측정 가능해야 함
- "어떻게 달성 여부를 알 수 있는가"
- 0~100% 또는 구체적 수치 목표
O1: {목표}
KR1: {지표} {현재값} → {목표값}
KR2: {지표} {현재값} → {목표값}
KR3: {지표} {현재값} → {목표값}
Step 4: 신뢰도 체크
각 KR에 달성 가능성 점수:
| 점수 | 의미 |
|---|---|
| 0.3 | 야심적 (stretch goal) |
| 0.5 | 도전적이지만 가능 |
| 0.7 | 충분히 달성 가능 |
| 1.0 | 너무 쉬움 (목표 상향 필요) |
이상적인 분포: 대부분 0.5~0.7
Step 5: 파일 저장
출력: docs/okr/current.md
# OKR — {YYYY} Q{N}
## 기간
{시작일} ~ {종료일}
## Objectives & Key Results
### O1: {목표}
| # | Key Result | 현재 | 목표 | 진행률 | 신뢰도 |
|---|-----------|------|------|--------|--------|
| KR1 | {핵심결과} | {현재} | {목표} | 0% | 0.5 |
| KR2 | {핵심결과} | {현재} | {목표} | 0% | 0.7 |
### O2: {목표}
| # | Key Result | 현재 | 목표 | 진행률 | 신뢰도 |
|---|-----------|------|------|--------|--------|
| KR1 | ... | ... | ... | 0% | ... |
## 전체 진행률: 0%
Mode: Review (진행률 점검)
docs/okr/current.md를 읽고:
- 각 KR의 현재 상태를 현재 CLI의 질문 방식으로 확인
- 진행률 업데이트
- 위험 KR 식별 (진행률 < 기대 진행률)
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.
- 4d ago First seen · 196 lines · 59 tokens per session scan A d1f5e61ea6d0
okr is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,500 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 2026-09-03.
Other skills, from other repositories
factory-close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
factory-submit
Move the current branch's Linear issue to "In Review".
factory-setup-linear
Configure portable Linear workflow settings in .factory-kit/linear.json, migrating legacy .claude/linear.json settings when present.
factory-entry
Load a Linear issue into context and enter plan mode for a focused session.
factory-standup
Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog.
implement-batch
Use when you want to implement the next batch of a plan. Handles module implementation, testing, and validation.