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 forecast-risk-briefgit 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/forecast-risk-brief)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/forecast-risk-brief"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/forecast-risk-brief/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/forecast-risk-brief"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/forecast-risk-brief.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 | $0.00066 | $0.00936 |
| Opus 5 | $0.00033 | $0.00468 |
| Sonnet 5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
forecast-risk-brief 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forecast risk brief
Separate deal risk from data-quality risk. Then tell leadership what to do this week.
A good brief shows which commit value is threatened, which is merely untrustworthy, and which intervention belongs to each. If the user wants one deal inspected, use deal-inspection-coach.
Deal risk. "Three commits have a hard stop: legal review cannot finish before quarter-end. That value is exposed even if the CRM is complete."
Data-quality risk. "Two more commits have no buyer next step and a close date that moved twice with no new evidence. You cannot tier them. They are indeterminate, not probably fine."
If evidence confidence is being used as close likelihood, rewrite it.
Confirm Inputs First
Ask only for the inputs that change the brief:
- Forecast window, coverage (team, segment, region), as-of date, and currency
- Category definitions and what counts as buyer-confirmed progression
- The snapshot: category, stage, amount, close date, last stage change, next step
- Available risk signals and any historical cycle-time baseline
- The leadership need: accuracy, intervention, or board summary
If a field is missing, leave it unknown. Do not invent amounts, dates, categories, or thresholds.
Read The Right Reference
Read references/forecast-risk-framework.md before assigning a risk tier. Read references/source-system-guide.md when the source is a CRM or BI export.
Default Workflow
- Freeze the snapshot. One as-of date, one currency, one category set. Done when totals reconcile to the export and mixed currencies or duplicate IDs are flagged.
- Keep the seller category separate from your tier. Commit is what they recorded. Risk is what the evidence supports. Done when you have not "corrected" a category in the system.
- Run the same checks on every in-scope deal. Time feasibility, buyer-confirmed progression, next step, stakeholders, commercial path, date stability. Use the org's model if they supplied one. Otherwise show the decisive check, not a homemade score. Done when each deal is low, moderate, high, or indeterminate.
- Rate evidence confidence on its own. Completeness, freshness, conflicts, baseline quality. Missing critical fields cannot be rescued by a full set of low-value fields. Low risk requires high confidence.
- Aggregate for leadership. Value and count by tier, category, rep, segment, stage, and close timing. Keep indeterminate outside the low/moderate/high totals.
- Apply the risk-confidence matrix. High risk with usable evidence: intervene on the named blocker. High risk with low confidence: verify first. Indeterminate: name the smallest fact that would unlock a tier.
- Assign interventions. Owner, confirmed or proposed date, verification check. A date you created is proposed. Escalate concentration only against a tolerance the user supplied; otherwise show the exposure and ask.
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 · 76 lines · 66 tokens per session scan A 59ae3d7f8c0e
forecast-risk-brief is a skill published in the GitHub repository nthnclrk/enablement-skills (13 stars, last pushed 22d ago), licensed MIT. It adds 66 tokens to every session and 936 once invoked, about $0.0003 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…