phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.
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.
git clone --depth 1 https://github.com/phuryn/pm-skillsWrote 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/commands/phuryn/pm-skills/plan-okrs)<a href="https://agentmods.dev/commands/phuryn/pm-skills/plan-okrs"><img src="https://agentmods.dev/badge/commands/phuryn/pm-skills/plan-okrs.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 | $0.00017 | $0.00870 |
| Opus 5 | $0.00009 | $0.00435 |
| Sonnet 5 | $0.00003 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
plan-okrs 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plan-okrs — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan-okrs -- Team OKR Planning
Generate well-structured OKRs that connect team work to company strategy. Produces 3 OKR sets with qualitative objectives and quantitative key results.
Invocation
/plan-okrs Growth team Q2 — company goal is 50% ARR increase
/plan-okrs Onboarding squad aligned to "improve activation rate"
/plan-okrs [upload company OKRs or strategy doc]
Workflow
Step 1: Gather Context
Ask the user:
- What team or product area are these OKRs for?
- What time period? (quarterly is standard, but could be annual or custom)
- What are the company-level objectives these should ladder up to?
- What happened last quarter? (hits, misses, learnings)
- Any constraints or known priorities?
Accept company OKRs or strategy documents as uploads.
Step 2: Generate OKRs
Apply the brainstorm-okrs skill:
- Create 3 OKR sets (Objective + 3-5 Key Results each)
- Objectives: Qualitative, inspiring, ambitious but achievable, action-oriented
- Key Results: Quantitative, measurable, time-bound, have clear owners
- Ensure OKRs ladder to company objectives with visible connection
- Balance leading indicators (activity) with lagging indicators (outcomes)
Step 3: Validate Quality
Check each OKR against best practices:
- Is the Objective inspiring? (Would you rally a team around it?)
- Are Key Results measurable? (Can you check completion with data, not judgment?)
- Are targets ambitious but not demoralizing? (70% achievement = well-calibrated)
- Are there 3-5 KRs per Objective? (More = unfocused)
- Do KRs avoid gaming? (e.g., "ship 5 features" incentivizes shipping junk)
Flag any issues and suggest improvements.
Step 4: Present and Iterate
## Team OKRs: [Team Name] — [Period]
**Aligned to**: [Company Objective(s)]
### Objective 1: [Inspiring qualitative statement]
| # | Key Result | Baseline | Target | Owner |
|---|-----------|----------|--------|-------|
| KR1 | [measurable result] | [current] | [target] | [team/person] |
| KR2 | ... | ... | ... | ... |
| KR3 | ... | ... | ... | ... |
### Objective 2: [Inspiring qualitative statement]
[same format]
### Objective 3: [Inspiring qualitative statement]
[same format]
### Alignment Map
Company Objective → Team Objective → Key Results → Expected Impact
### Scoring Guide
- 0.0-0.3: Significant miss — investigate and learn
- 0.4-0.6: Progress made but fell short
- 0.7-0.9: Well-calibrated stretch goal — this is the target zone
- 1.0: Either nailed it or target wasn't ambitious enough
### Check-in Cadence
- **Weekly**: Quick traffic-light update on each KR
- **Mid-quarter**: Deep review, adjust targets if context changed
- **End of quarter**: Score, reflect, feed into next quarter
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 · 99 lines · 17 tokens per session scan A 64fa936f4d2c
plan-okrs is a command published in the GitHub repository phuryn/pm-skills (26,066 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 870 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
retro
Facilitate a post-launch or sprint retrospective anchored to OKRs.
discover
Run a full discovery cycle — problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and OST mapping — from a rough idea to validated opportunity.
set-okrs
Structure OKRs — define objectives, write measurable key results, align to strategy, stress-test for quality, and cascade across teams.
onboarding
Set up PM Copilot — a guided wizard that builds your persistent memory profile so every future session is grounded in your product context.
plan-sprint
Plan the upcoming sprint — epic breakdown, user story decomposition, RICE prioritization, dependency check, and capacity allocation.
roadmap
Build or review your roadmap — OKR alignment, Now/Next/Later structuring, dependency mapping, and stakeholder views, pulling live Linear/Jira state.