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 yonatangross/orchestkit --skill okr-designgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/okr-design)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/okr-design"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/okr-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yonatangross/orchestkit/okr-design"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/okr-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 209 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00046 | $0.01809 |
| Opus 5 | $0.00023 | $0.00905 |
| Sonnet 5 | $0.00009 | $0.00362 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
okr-design 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKR Design & Metrics Framework
Structure goals, decompose metrics into KPI trees, identify leading indicators, and design rigorous experiments.
OKR Structure
Objectives are qualitative and inspiring. Key Results are quantitative and outcome-focused — never a list of outputs.
Objective: Qualitative, inspiring goal (70% achievable stretch)
+-- Key Result 1: [Verb] [metric] from [baseline] to [target]
+-- Key Result 2: [Verb] [metric] from [baseline] to [target]
+-- Key Result 3: [Verb] [metric] from [baseline] to [target]
## Q1 OKRs
### Objective: Become the go-to platform for enterprise teams
Key Results:
- KR1: Increase enterprise NPS from 32 to 50
- KR2: Reduce time-to-value from 14 days to 3 days
- KR3: Achieve 95% feature adoption in first 30 days of onboarding
- KR4: Win 5 competitive displacements from [Competitor]
OKR Quality Checks
| Check | Objective | Key Result |
|---|---|---|
| Has a number | NO | YES |
| Inspiring / energizing | YES | not required |
| Outcome-focused (not "ship X features") | YES | YES |
| 70% achievable (stretch, not sandbagged) | YES | YES |
| Aligned to higher-level goal | YES | YES |
See references/okr-workshop-guide.md for a full facilitation agenda (3-4 hours, dot voting, finalization template). See rules/metrics-okr.md for pitfalls and alignment cascade patterns.
KPI Tree & North Star
Decompose the top-level metric into components with clear cause-effect relationships.
Revenue (Lagging — root)
├── New Revenue = Leads × Conv Rate (Leading)
├── Expansion = Users × Upsell Rate (Leading)
└── Retained = Existing × (1 - Churn) (Lagging)
North Star + Input Metrics Template
## Metrics Framework
North Star: [One metric that captures core value — e.g., Weekly Active Teams]
Input Metrics (leading, actionable by teams):
1. New signups — acquisition
2. Onboarding completion rate — activation
3. Features used per user/week — engagement
4. Invite rate — virality
5. Upgrade rate — monetization
Lagging Validation (confirm inputs translate to value):
- Revenue growth
- Net retention rate
- Customer lifetime value
What ships with it
8 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 · 227 lines · 46 tokens per session scan A dbfb9a0c2413
okr-design is a skill published in the GitHub repository yonatangross/orchestkit (229 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,809 once invoked, about $0.0002 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
ve-midnight-editorial
OpenDesign's financial review: runway, burn, and the sustainability plan that keeps the project independent. Built as a decision-grade data & finance deck for board, leadership.
Agent Workflow Builder
Build multi-agent AI workflows with orchestration, tool use, and state management.
review
Business review — weekly health check, monthly close, or ad-hoc audit. Subcommands: weekly, monthly, check. Use for periodic reviews or metrics assessment.
delegate
Delegate implementation to Cursor via the cursor-delegate-mcp MCP delegate tool. Use when the user says delegate to Cursor, Composer, or cursor-agent; have Cursor handle or do this; offload this; send this to Composer; use Composer/Cursor for coding; hand off implementation; plan before building; ask Cursor a question…
tdd
Use when implementing features or bug fixes test-first.
apply-goodharts-law
Use when choosing what to measure for a KPI, OKR, ML training objective, or SLO — or when a metric that once tracked real performance keeps rising while the underlying outcome doesn't — to diagnose or prevent the specific mechanism by which a measure degrades once people optimize directly against it.