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 pm-dashboardgit 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/pm-dashboard)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/pm-dashboard"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/pm-dashboard/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/pm-dashboard"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/pm-dashboard.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 | $0.00035 | $0.01059 |
| Opus 5 | $0.00017 | $0.00530 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
pm-dashboard 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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM Dashboard: Product Status Overview
You produce a single-page status dashboard by reading everything in the knowledge/ directory and pulling live data from any available MCP integrations.
Before Running
- Check that
knowledge/exists. If not, tell the user: "No knowledge base found. Run/pm-setupfirst." - Read
knowledge/pm-context.mdto get product context and preferences.
Data Collection
Read all available knowledge files. For each section below, note what data exists and what is missing.
Files to Read
Read these files (skip any that don't exist):
knowledge/pm-context.md: Product contextknowledge/okrs.md: OKR definitions and progressknowledge/team.md: Team infoknowledge/roadmap/*.md: Roadmap itemsknowledge/sprints/*.md: Sprint scoping (look for the most recent)knowledge/decisions/*.md: Recent decisions (last 5)knowledge/launches/*.md: Upcoming or recent launchesknowledge/metrics/*.md: Latest metrics snapshotsknowledge/feedback/synthesis-*.md: Latest feedback synthesisknowledge/priorities/*.md: Current prioritizationknowledge/experiments/*.md: Active experiments
MCP Integrations (Check and Use If Available)
Check if these tools are accessible. Use them if they are, skip gracefully if not.
Linear / Jira (project management tools):
- Try to list current sprint tickets, their status, and assignees
- Pull velocity or burndown if available
- Note blocked tickets
GitHub (source control):
- Check for open PRs and their review status
- Look for recent deployments or releases
- Note any failing CI checks
Slack (communication):
- Look for recent product-related threads or escalations
- Check for unresolved questions in product channels
For each integration that is NOT available, add a small note in the dashboard: "(Live data unavailable, install {tool} MCP for real-time updates)"
Dashboard Output
Present the dashboard in this format:
# Product Dashboard: {product_name}
*Generated: {today's date and time}*
---
## OKR Progress
{For each objective, show the objective and each key result with progress if known}
{If no progress data, show the OKRs and mark "Progress: not yet tracked"}
| Objective | Key Result | Status |
|-----------|-----------|--------|
| {obj} | {kr} | {status or "Not tracked"} |
---
## Sprint Status
{Current sprint name/number if known}
{Ticket counts by status: To Do, In Progress, Done}
{Blocked items highlighted}
{If no sprint data: "No sprint data. Run /sprint-scope to plan your next sprint."}
---
## Recent Decisions
{Last 3-5 decisions with date, title, and outcome}
{If none: "No decisions recorded. Use /decision-record after your next key decision."}
---
## Open Blockers
{Any blocked items from sprint, launches, or decisions}
{If none: "No blockers identified."}
---
## Upcoming Launches
{Next 2-3 launches with target date and readiness status}
{If none: "No launches planned. Use /launch when you're ready."}
---
## Metrics Snapshot
{Latest values for key metrics from pm-context.md}
{Trends if multiple snapshots exist}
{If no data: "No metrics recorded. Use /metrics-check to start tracking."}
---
## Active Experiments
{Any running A/B tests or experiments with status}
{If none: "No active experiments."}
---
## Customer Feedback Themes
{Top 3 themes from latest feedback synthesis}
{If none: "No feedback synthesized. Use /feedback-synthesis to analyze customer feedback."}
---
## What Needs Attention
{Synthesize: what looks off, what's overdue, what's at risk}
{Specific recommendations with skill commands to resolve each}
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.
- 9d ago First seen · 133 lines · 35 tokens per session scan A 6d5cb2c03984
pm-dashboard is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,059 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: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.
recipe-plan
Create work plan from design document and obtain plan approval.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
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:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
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.