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 nthnclrk/enablement-skills --skill pipeline-stage-definition-and-exit-criteriagit clone --depth 1 https://github.com/nthnclrk/enablement-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/nthnclrk/enablement-skills/pipeline-stage-definition-and-exit-criteria)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/pipeline-stage-definition-and-exit-criteria"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/pipeline-stage-definition-and-exit-criteria/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/nthnclrk/enablement-skills/pipeline-stage-definition-and-exit-criteria"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/pipeline-stage-definition-and-exit-criteria.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 | $0.00073 | $0.00915 |
| Opus 5 | $0.00036 | $0.00458 |
| Sonnet 5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
pipeline-stage-definition-and-exit-criteria 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline stage definition and exit criteria
Write stages as buyer-signal checkpoints. If a seller can pass a stage by sending a deck, the stage is broken.
A good stage says what the buyer decided and what proof a manager can inspect. If the user wants one live deal reviewed, use deal-inspection-coach. If they want a period forecast, use forecast-risk-brief.
Buyer-signal exit. "Discovery exits when the buyer names the problem, its cost, and why it is funded this cycle. Required proof: a buyer-authored problem statement or recorded confirmation from the economic buyer."
Activity checklist. "Discovery exits when the AE logs a discovery call and fills the MEDDPICC fields."
If two stages can be true at once, they are not stages yet.
Confirm Inputs First
Ask only for the inputs that change the model:
- Current stage map and who operates it
- Historical stage evidence for a representative period, if it exists
- Target motions and the qualification method in use
- The inspection and forecast problems this redesign must fix
If history is missing, label the model a hypothesis. Do not invent conversion rates, aging norms, or CRM behavior.
Read The Right Reference
Read references/stage-exit-framework.md before writing stage cards or governance. Read references/source-system-guide.md when the output must later map into CRM fields and reporting.
Default Workflow
- Establish the baseline. Find stages that are vague, skipped, slow, frequently regressed, or weakly tied to outcomes. Record data gaps. Done when you can name the broken stages and what evidence you lack.
- Give each stage one buyer signal. One purpose. One reason to move. Done when you can say the buyer state in a sentence a manager would use in inspect.
- Set entry, exit, and proof. Required proof blocks progression except through a documented exception. Recommended proof coaches; it does not block. Keep required proof to the minimum buyer-validated evidence that reduces that stage's named risk.
- Name the anti-patterns. Sent proposal, booked meeting, populated field, and seller assertion are activity until buyer evidence shows what changed. Write how managers handle exceptions.
- Map to the qualification method. Attach only the MEDDPICC, SPICED, or local checks that belong to this stage's risk. Do not reprint the whole framework on every card.
- Backtest before rollout. Apply the criteria to won, lost, no-decision, and open deals. Report how many would progress, remain, regress, or need an exception. If history cannot support that, define a pilot.
- Set inspection and rollback. Manager and RevOps cadence. Success thresholds for completeness, exception rate, aging, conversion, and forecast variance. Named rollback owner and restoration path.
- Map to systems last. Design the operating logic first. Then recommend fields, notes, and dashboards. Do not move live opportunities or flip required fields without explicit approval.
What ships with it
3 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.
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.
- 12d ago First seen · 75 lines · 73 tokens per session scan A 98757802b11d
pipeline-stage-definition-and-exit-criteria is a skill published in the GitHub repository nthnclrk/enablement-skills (13 stars, last pushed 23d ago), licensed MIT. It adds 73 tokens to every session and 915 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…