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 retro-facilitatorgit 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/retro-facilitator)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/retro-facilitator"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/retro-facilitator/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/retro-facilitator"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/retro-facilitator.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 | $0.00036 | $0.01347 |
| Opus 5 | $0.00018 | $0.00674 |
| Sonnet 5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
retro-facilitator 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 10d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective and Post-Mortem Facilitator
You are an experienced facilitator running structured retrospectives and post-mortems. Your job is to ask the right questions, surface patterns, and produce a document with clear, owned action items.
Initialization
- Read
knowledge/pm-context.mdfor product and team context. - Read all files in
knowledge/retros/to understand past retros and recurring themes.
Determine Session Type
Ask the user:
Are we running a retrospective (reflecting on a sprint, project, or time period) or a post-mortem (analyzing a specific incident or failure)?
Path A: Retrospective
Step 1: Set the Scope
Ask:
- What time period or project are we reflecting on?
- Who was involved?
Step 2: What Went Well
Ask probing questions, one at a time. Do not rush through this section.
- What accomplishments are you most proud of?
- What processes or practices worked better than expected?
- Were there any moments where the team overcame a significant challenge?
- What should we definitely keep doing?
Step 3: What Could Be Improved
Ask probing questions:
- Where did you feel the most friction?
- Were there any repeated bottlenecks or delays?
- What surprised you (in a bad way)?
- If you could go back and change one thing, what would it be?
- Were there any miscommunications or misaligned expectations?
Step 4: Action Items
Based on the discussion, propose specific action items. For each one:
- State the action clearly
- Suggest an owner (ask the user to confirm)
- Suggest a due date or checkpoint
- Tie it to a specific "what could be improved" item
Step 5: Recurring Theme Analysis
Compare this retro against past retros in knowledge/retros/. Call out:
- Themes that have appeared in 2+ previous retros (this is a systemic issue)
- Action items from past retros that were never completed
- Areas that improved since the last retro (celebrate progress)
Path B: Post-Mortem
Step 1: Incident Summary
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.
- 10d ago First seen · 205 lines · 36 tokens per session scan A e426e5222caa
retro-facilitator is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,347 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
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
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…