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 indranilbanerjee/neels-plugins --skill case-study-plangit clone --depth 1 https://github.com/indranilbanerjee/neels-pluginsWrote 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/indranilbanerjee/neels-plugins/case-study-plan)<a href="https://agentmods.dev/skills/indranilbanerjee/neels-plugins/case-study-plan"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/case-study-plan/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/indranilbanerjee/neels-plugins/case-study-plan"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/neels-plugins/case-study-plan.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 | $0.00026 | $0.01604 |
| Opus 5.5 | $0.00010 | $0.00642 |
| Sonnet 5.5 | $0.00005 | $0.00321 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
case-study-plan 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 2d 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
88% identical to case-study-plan — 0 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:case-study-plan
Purpose
Generate a structured case study creation plan with interview framework, data visualization approach, format variations, and distribution strategy. Produces a complete blueprint for building compelling proof-of-results content that drives sales enablement and builds credibility.
Input Required
The user must provide (or will be prompted for):
- Client or project to feature: The specific client engagement, campaign, or project that will be showcased
- Challenge or problem addressed: The business problem, market pressure, or growth obstacle the client was facing before the engagement
- Solution implemented: The services, campaigns, strategies, or tools deployed to address the challenge
- Results achieved: Quantitative outcomes (revenue lift, traffic growth, conversion improvement, cost reduction) and qualitative outcomes (brand perception, team capability, process improvement)
- Timeline of engagement: Duration of the project or campaign — start date, key milestones, and current status
- Permission status: Whether the client has approved public use of their name, data, and story — or if anonymization is required
- Target audience for the case study: Who will read or watch it — prospects in the same industry, C-suite decision-makers, marketing managers, procurement teams, or general audience
- Desired formats: Which output formats are needed — PDF white paper, website page, presentation deck, video testimonial, social media snippets, or sales one-pager
- Industry vertical: The client's industry for contextual benchmarking and relevance targeting
- Competitive context: What alternatives the client considered and why they chose this approach
Process
- Load brand context: Read
~/.claude-marketing/brands/_active-brand.jsonfor the active slug, then load~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at~/.claude-marketing/brands/{slug}/guidelines/_manifest.json— if present, load restrictions and relevant category files. Check for custom templates at~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults. - Structure the CSR narrative: Build the Challenge-Solution-Results framework with sub-sections — situation overview, specific pain points, goals at project start, strategic approach, tactical execution, implementation timeline, quantitative results, qualitative impact, and future outlook. Identify the emotional arc that makes the story compelling, not just informative.
- Develop client interview questions: Create 15-20 interview questions organized by section — background and context (company size, industry pressures, previous attempts), challenge deep-dive (symptoms, root causes, business impact of inaction), solution experience (selection criteria, onboarding, collaboration quality), results and impact (measurable outcomes, unexpected benefits, team reaction), and forward-looking (ongoing plans, what they would tell peers).
- Plan internal team interview questions: Draft 10 questions for internal team members who worked on the engagement — strategic rationale, technical approach, challenges encountered during delivery, key turning points, and lessons learned that could inform future engagements.
- Identify data points and visualizations needed: Map every quantitative result to a visualization type — before/after bar charts, timeline growth curves, funnel improvement diagrams, ROI waterfall charts, and comparison tables. Specify which data needs to be collected, verified, and approved by the client before publication.
- Design format variations: Create specifications for each requested output format — PDF white paper (4-6 pages, designed layout with pull quotes and charts), web page (SEO-optimized with structured data markup), presentation deck (8-12 slides for sales meetings), video testimonial script (2-3 minute interview-based script outline), social media snippets (pull quotes, stat cards, carousel posts), and sales one-pager (front-and-back summary for leave-behinds).
- Create distribution strategy: Plan where and how the case study will be published and promoted — website case study library, sales enablement materials, email nurture sequences, social media campaigns, PR outreach, paid promotion, conference presentations, and partner co-marketing opportunities.
- Build approval workflow and permission checklist: Define the full approval process — internal review (legal, marketing, account team), client review (point of contact, legal, executive sign-off), data accuracy verification, quote approval, logo and brand usage permission, and timeline for each review stage.
- Write draft executive summary: Compose a 150-200 word executive summary that captures the full story arc — who the client is, what they faced, what was done, and what resulted. This summary serves as the foundation for all format variations and distribution copy.
- Plan visual assets needed: Specify all visual elements required — client logo (with usage permissions), data visualization charts, photography (team photos, office shots, product images), branded design templates, infographic elements, pull quote cards, and video b-roll if applicable.
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.
- 2d ago First seen · 62 lines · 26 tokens per session scan A e84ddc13ee6c
case-study-plan is a skill published in the GitHub repository indranilbanerjee/neels-plugins (6 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,604 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to case-study-plan, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
continuous-improvement-loop
Run the Part 12 continuous improvement loop into a quarterly brief for leadership. "produce the quarterly improvement brief".
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
attribution-report
Run attribution on real conversion paths, comparing models. "which channels actually drive revenue".
validate-output
Validate content structure against a schema: sections, word counts. "scan for leftover placeholders".
add-integration
Add a custom MCP integration: scaffold the server, write .mcp.json, test it. "add a new MCP server".
client-proposal
Draft a client proposal or RFP response: scope, deliverables, KPIs, pricing tiers. "respond to this RFP".