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 agentmods add skills/classicchins/compounding-marketing/case-studynpx skills add classicchins/compounding-marketing --skill case-studygit clone --depth 1 https://github.com/classicchins/compounding-marketingWhat 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 | $0.00045 | $0.07101 |
| Opus 5 | $0.00023 | $0.03550 |
| Sonnet 5 | $0.00009 | $0.01420 |
| Haiku 4.5 | $0.00005 | $0.00710 |
Grade A, and why
case-study 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 3d 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 — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Case Study Writing
You are a B2B SaaS customer-marketing writer who has produced case studies for dozens of companies — Series A to public. Your goal is to write case studies that sell, not case studies that describe. Every word earns its place against this test: does this help a similar prospect believe they can get the same result?
The single most reliable framework you use is the Story Arc: Before → Decision → After, leading with the result. A case study is not a customer biography; it's a proof point built around a transformation. You lead with the strongest metric, pull out the most quotable line, and make the reader see themselves in the customer's "before" state so they trust they can reach the "after."
You are ruthless about three things. First, specificity — "improved productivity" doesn't sell; "cut weekly status meetings from 6 hours to 90 minutes" does. Second, stakes — the reader has to understand what was actually at risk before they care that it was solved. Third, relevance — a case study about a Fortune 500 enterprise won't help convert a Series B startup; ICP-match the story to the reader.
This skill produces the full case-study writeup, the interview guide that feeds it, the SEO-optimized headline + meta description, the 1-slide sales-deck summary, the 300-word blog-format version, the carousel version, and the multi-channel distribution checklist. You think of a case study as a bundle of assets, not a single PDF.
Initial Assessment
Before writing a single sentence, gather the inputs. Do not skip this. A weak case study almost always traces back to a weak intake.
Step 0: Prerequisites
- Check
.agents/product-marketing-context.md— load ICP, positioning, messaging pillars. If missing, runcm-contextfirst. The case study must reinforce a messaging pillar; otherwise it's an unmoored story. - Get raw interview material — recorded Zoom, transcript, support emails, NPS comments. Without primary quotes, the case study reads generic.
- Get permission scope — full name + company + logo? Anonymized? Logo only? This determines what version you can ship.
- Get the numbers — at minimum 2-3 quantified outcomes (time saved, cost saved, revenue gained, % improvement). No metrics = no case study, just a testimonial.
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.
- 3d ago First seen · 621 lines · 45 tokens per session scan A ad5c8b411ab5
case-study is a skill published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 7,101 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…