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 agentmods add skills/rampstackco/claude-skills-pm/beta-program-managementnpx skills add rampstackco/claude-skills-pm --skill beta-program-managementgit clone --depth 1 https://github.com/rampstackco/claude-skills-pmWrote 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/rampstackco/claude-skills-pm/beta-program-management)<a href="https://agentmods.dev/skills/rampstackco/claude-skills-pm/beta-program-management"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills-pm/beta-program-management.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 | $0.00155 | $0.04838 |
| Opus 5 | $0.00077 | $0.02419 |
| Sonnet 5 | $0.00031 | $0.00968 |
| Haiku 4.5 | $0.00015 | $0.00484 |
Grade A, and why
beta-program-management 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 4d 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.
This is a copy
95% identical to beta-program-management — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beta Program Management
A senior product leader's playbook for running betas that produce real signal. Closed and open betas, alpha programs, design partner programs, early access. Participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional feedback loops, clear graduation criteria).
Most betas underperform. Teams ship a beta because they think they should run a beta; participants are recruited loosely or open-flooded; feedback is collected ad-hoc through whatever channels exist; the decision to graduate to GA happens on calendar rather than on signal. The beta produced activity but not learning; the team launches with the same uncertainty they had before the beta.
This skill is the discipline that turns betas into decision input. Calibrated cohorts who match the post-launch user profile. Structured feedback that captures what the team needs to know. Mid-beta triage that uses what is being learned. Graduation criteria that distinguish "ready" from "we are tired of running the beta." The discipline is not bureaucratic; it is the difference between a beta that informs the GA launch and a beta that produces noise.
The voice is the senior product leader who has run betas with real signal and watched plenty of betas produce nothing. Concrete, opinionated about what produces signal, willing to call out where beta programs slide into ceremony.
When to use this skill: planning a beta for an upcoming launch, auditing why prior betas have not produced actionable signal, designing the beta participant experience, or deciding whether a feature is ready to graduate from beta to GA.
What this skill is for
This skill spans beta program design and execution. The PM and engineering distinction:
feature-flaggingis rollout mechanics; the technical layer for controlling who gets which features.beta-program-management(this skill) is participant management and feedback discipline; the human layer.feature-launch-playbookis the full launch (post-GA); this skill is what happens BEFORE GA.experiment-designis rigorous A/B testing; betas are softer, qualitative-leaning, smaller-N.user-feedback-aggregationis ongoing feedback streams; beta feedback is bounded to the beta period.discovery-research-synthesisis one-off discovery research; betas are validation-stage rather than discovery-stage.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/beta-onboarding-templates.md 10 KB
- references/beta-to-ga-graduation-criteria.md 11 KB
- references/beta-type-decisions.md 10 KB
- references/beta-wind-down-communication.md 9.3 KB
- references/cohort-sizing-patterns.md 8.7 KB
- references/common-beta-failures.md 10 KB
- references/feedback-collection-patterns.md 11 KB
- references/mid-beta-triage-and-iteration.md 9.4 KB
- references/participant-selection-criteria.md 9.9 KB
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.
- 4d ago First seen · 313 lines · 155 tokens per session scan A 5142f007fa6d
beta-program-management is a skill published in the GitHub repository rampstackco/claude-skills-pm (4 stars, last pushed 1mo ago), licensed MIT. It adds 155 tokens to every session and 4,838 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to beta-program-management, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
replit-deck
For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident…
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
html-ppt-knowledge-arch-blueprint
OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.
deck-open-slide-canvas
OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.
html-ppt-graphify-dark-graph
OpenDesign's feature business case for the plugin marketplace: the user pain, options, tradeoffs, and the measure of success. Built as a decision-grade product management deck for PM, eng, design, leadership.
beads
Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or…