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 deal-inspection-coachgit 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/deal-inspection-coach)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/deal-inspection-coach"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/deal-inspection-coach/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/deal-inspection-coach"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/deal-inspection-coach.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 | $0.00080 | $0.00981 |
| Opus 5 | $0.00040 | $0.00491 |
| Sonnet 5 | $0.00016 | $0.00196 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
deal-inspection-coach 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.
Deal inspection coach
Inspect one deal for buyer proof. Seller activity is not progress.
A good inspection tells a manager what the buyer has confirmed, what is still unknown, and the one move that changes the deal. If the user wants a portfolio forecast, use forecast-risk-brief. If they want a buyer-shared plan, use mutual-action-plan-builder.
Buyer proof. "Economic buyer confirmed this is funded this quarter. Security is in their queue with a named owner. Next step is their commercial review on 3 Sep."
Seller activity. "Twelve emails last week. Demo completed. Next step is follow up. Stage is Proposal because the deck went out."
If a manager cannot tell buyer-confirmed from internally asserted, it is not done.
Confirm Inputs First
Ask only for the inputs that change the diagnosis:
- The one opportunity, as-of date, claimed stage, and inspection objective
- The evidence packet: CRM, buyer comms, calls, MAP, proposal, procurement
- The team's stage criteria and qualification method, if they have one
- Whether the output is internal-only
If a fact is missing, leave it unknown. Do not invent CRM fields, amounts, dates, stakeholders, or commitments.
Read The Right Reference
Read references/deal-inspection-framework.md before rating evidence, stage validity, or risk. Read references/source-system-guide.md when evidence comes from CRM, conversation intelligence, or email summaries.
Default Workflow
- Name the job. One opportunity. One decision: validate stage, recover momentum, test forecast confidence, or choose an intervention. Done when you can say which, and why the others wait.
- Build the evidence ledger. For each material claim: source, source date, buyer-confirmed or internally asserted, and current / stale / missing / conflicted. Done when every claim you will use has a status.
- Test stage validity. Match evidence to the team's exit criteria. If they have none, report buying-path readiness. Do not invent a stage gate. Done when each criterion is met, not met, conflicted, stale, or unknown.
- Walk the buying path. Problem priority, value, stakeholders, criteria, process, alternatives, execution, timing. An unanswered question is not negative evidence. Done when you can name the open buyer decision that matters most.
- Separate risk from gap. A risk is a supported condition that can kill or slip the deal. A gap is a consequential unknown. They need different actions. Skip a numeric score unless the org supplied a model.
- Pick the next moves. Few actions. Each needs an owner, the buyer progress it creates or the unknown it closes, and a verification check. Label dates as proposed unless the buyer confirmed them.
- Give the manager the inspect. The question to ask, the evidence to open, the decision to make, and when to escalate. Recommend stage or CRM changes; do not apply them.
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 · 80 tokens per session scan A a025418f80ee
deal-inspection-coach is a skill published in the GitHub repository nthnclrk/enablement-skills (13 stars, last pushed 23d ago), licensed MIT. It adds 80 tokens to every session and 981 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…