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/product-on-purpose/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/product-on-purpose/pm-skills/workflow-post-launch-learning)<a href="https://agentmods.dev/commands/product-on-purpose/pm-skills/workflow-post-launch-learning"><img src="https://agentmods.dev/badge/commands/product-on-purpose/pm-skills/workflow-post-launch-learning.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 | $0.00019 | $0.00353 |
| Opus 5 | $0.00010 | $0.00177 |
| Sonnet 5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
workflow-post-launch-learning 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.
What it actually says
Run the Post-Launch Learning workflow to set up measurement, evaluate results, and capture learnings after a feature ships.
This workflow uses multiple skills in sequence. For each step, read the skill instructions and follow them to create the artifact.
Workflow Steps
Step 1: Instrumentation Spec
Use the measure-instrumentation-spec skill from skills/measure-instrumentation-spec/SKILL.md.
Define event tracking and analytics instrumentation requirements for the shipped feature.
Step 2: Dashboard Requirements
Use the measure-dashboard-requirements skill from skills/measure-dashboard-requirements/SKILL.md.
Specify the analytics dashboard including metrics, visualizations, and data sources.
Step 3: Experiment Results
Use the measure-experiment-results skill from skills/measure-experiment-results/SKILL.md.
Document the results of the feature launch with analysis and recommendations.
Step 4: Retrospective
Use the iterate-retrospective skill from skills/iterate-retrospective/SKILL.md.
Facilitate a team retrospective covering the full feature lifecycle.
Step 5: Lessons Log
Use the iterate-lessons-log skill from skills/iterate-lessons-log/SKILL.md.
Distill retrospective findings into durable lessons for organizational memory.
Output
Create all five artifacts in sequence. Steps 1-2 should happen at or before launch; Steps 3-5 after data accumulates.
Reference the Post-Launch Learning workflow at _workflows/post-launch-learning.md for additional guidance.
Context from user: $ARGUMENTS
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 · 48 lines · 19 tokens per session scan A 9e6676fc5e79
workflow-post-launch-learning is a command published in the GitHub repository product-on-purpose/pm-skills (647 stars, last pushed 2d ago), licensed Apache-2.0. It adds 19 tokens to every session and 353 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
discover
Structured product discovery from problem to validated experiments.
okr-planning
Structured OKR creation aligned with company objectives.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
epic-dev
Epic/sprint development workflow with git worktrees, GitHub issues, and phased delivery.
triage
Triages an unprioritized list of bugs, debt, and tasks into a full MoSCoW breakdown with justification and an attack order.