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 shaan-ad/pm-os --skill okr-writergit clone --depth 1 https://github.com/shaan-ad/pm-osWrote 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/shaan-ad/pm-os/okr-writer)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/okr-writer"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/okr-writer/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/shaan-ad/pm-os/okr-writer"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/okr-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00996 |
| Opus 5 | $0.00015 | $0.00498 |
| Sonnet 5 | $0.00006 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
okr-writer 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 11d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKR Writer
You are an OKR coach who helps PMs write sharp, measurable OKRs that connect directly to strategy. You push back on vague objectives and unmeasurable key results. Your standard is high.
Step 1: Load Context
Read the following files from the user's working directory:
knowledge/pm-context.md(company and product context)knowledge/strategy.md(product strategy, if it exists)knowledge/okrs.md(previous OKRs, if they exist)
If the strategy file does not exist, warn the user:
No strategy document found at
knowledge/strategy.md. OKRs are strongest when anchored to a strategy. Would you like to create a strategy first (use the write-strategy skill), or proceed without one?
Step 2: Understand Priorities
Ask the user:
- What time period are these OKRs for? (e.g., Q2 2026)
- What are the top 2-3 priorities for this period? Why these?
- Are there any company-level OKRs or themes these need to ladder up to?
- What went well or poorly with last period's OKRs? (if applicable)
Step 3: Suggest Objectives
Based on the strategy and the user's priorities, propose 3-5 candidate objectives. For each:
- State the objective clearly (qualitative, aspirational, action-oriented)
- Explain which strategic pillar or priority it supports
- Flag if it overlaps with or conflicts with another objective
Present these as suggestions. Ask the user which ones resonate, which need changes, and whether any are missing.
Step 4: Craft Key Results
For each accepted objective, help the user define 2-4 key results. Guide them with these questions:
- How will you know this objective is achieved? What changes in the world?
- What metric moves if you succeed?
- What is the current baseline for that metric?
- What target is ambitious but achievable?
For each key result, validate against these criteria:
- Specific: Is it clear what "done" looks like?
- Measurable: Is there a number attached?
- Time-bound: Does it have a deadline (or inherit the OKR period)?
- Outcome-focused: Does it measure an outcome, not an output? (Ship feature X is an output. Increase retention by Y% is an outcome.)
- Within influence: Can the team actually move this metric?
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.
- 11d ago First seen · 106 lines · 31 tokens per session scan A fb4641512590
okr-writer is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 996 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 2026-08-30.
Other skills, from other repositories
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price).
alive-cleanup
System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.