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 ianklassen/pm-skills --skill scope-cutgit clone --depth 1 https://github.com/ianklassen/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/skills/ianklassen/pm-skills/scope-cut)<a href="https://agentmods.dev/skills/ianklassen/pm-skills/scope-cut"><img src="https://agentmods.dev/badge/skills/ianklassen/pm-skills/scope-cut/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/ianklassen/pm-skills/scope-cut"><img src="https://agentmods.dev/badge/skills/ianklassen/pm-skills/scope-cut.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 | $0.00120 | $0.01663 |
| Opus 5 | $0.00060 | $0.00831 |
| Sonnet 5 | $0.00024 | $0.00333 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
scope-cut 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Cut
The judgment this encodes
Most scope-cutting defaults to cutting whatever's easiest to cut, or whatever the loudest stakeholder didn't ask for. Both produce a smaller release. Neither reliably produces a release that still proves what it needed to prove.
The question that actually matters: what is this release for, and does the cut version still do that? Two releases can be the same size on a ticket board and be completely different in whether they were worth shipping.
The decision framework
0. Separate what you can cut from what you can only renegotiate
Before sorting anything, identify scope that isn't actually yours to cut:
- Publicly committed: named on a landing page, announced at an event, in a press release
- Contractually committed: in an SLA, a signed enterprise deal, a partner integration agreement
- Externally dependent: another team or partner has already built against it
These are not cut decisions. They're renegotiations or escalations, and treating them as cuts is how PMs blow up trust with marketing, sales, and partners. Route them out of the cut list first and handle them separately (see escalation-judgment). What remains is your actual decision space.
1. Name the riskiest assumption the release is meant to test
Every release exists to learn or prove something: that customers want this, that this technical approach scales, that this workflow reduces support load. If you can't name that in one sentence, stop and get that answer before cutting anything; you'll cut the wrong things.
2. Sort scope into three buckets, not two
- Load-bearing: removing it means the release no longer proves what it set out to prove. Two tests, both of which must pass: (a) does the customer-visible value survive this cut, and (b) can you still tell whether it worked? The second test catches things that look like decoration but aren't: instrumentation, analytics events, logging, a control group. Invisible to customers, load-bearing to the release, and the single most commonly mis-cut category in this whole framework.
- Supporting: makes the load-bearing part usable/credible but isn't itself the test. Candidate for cutting to a rougher version, not necessarily to zero.
- Decoration: exists because it's nice, was requested by one loud voice, or "we're already in there." First things to go, no negotiation.
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 · 100 lines · 0 tokens per session scan A 1c4e89c7bf88
scope-cut is a skill published in the GitHub repository ianklassen/pm-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,663 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
utility-pm-skill-builder
Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates through a Why Gate, classifies by type and phase, generates draft files, and writes to a staging area for review before promotion.
utility-pm-skill-iterate
Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback.
tool-note-and-vote
Structured group-decision mechanic that captures silent ideation, voting summaries, and Decider sign-off in a single bundled artifact. Use when a small team needs to make a fast decision with diverse input, when groupthink is a risk, or when a workshop moment demands silent contribution before discussion. Applicable…
utility-pm-workflow-builder
Guides a contributor from a workflow idea to a complete Workflow Implementation Packet (draft workflow file, draft workflow command, cross-cutting update checklist) in a staging area for review. Runs overlap analysis against the existing workflows with a Why Gate, then helps select and sequence skills with authored…
foundation-prioritized-action-plan
Produce a comprehensive, evidence-grounded prioritized action plan from any PM input (notes, transcripts, drafts, executive asks, Slack threads, or a raw situation). Outputs one saveable document with an executive summary, input mirror, situation classification (Cynefin), the binding constraint (Theory of…
deliver-prd
Creates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how success will be measured. Use when specifying features, epics, or product initiatives for engineering handoff.