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 jqaisystems/jqai-ai-skills --skill case-study-writergit clone --depth 1 https://github.com/jqaisystems/jqai-ai-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/jqaisystems/jqai-ai-skills/case-study-writer)<a href="https://agentmods.dev/skills/jqaisystems/jqai-ai-skills/case-study-writer"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/case-study-writer/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/jqaisystems/jqai-ai-skills/case-study-writer"><img src="https://agentmods.dev/badge/skills/jqaisystems/jqai-ai-skills/case-study-writer.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 | $0.00096 | $0.00671 |
| Opus 5 | $0.00048 | $0.00336 |
| Sonnet 5 | $0.00019 | $0.00134 |
| Haiku 4.5 | $0.00010 | $0.00067 |
Grade A, and why
case-study-writer 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Study Writer
Overview
Use this skill to turn private project work into public-safe proof: concise case studies that explain the problem, workflow, outcome, and adaptation value without exposing source code, credentials, raw prompts, logs, databases, client data, or private implementation details.
Workflow
- Clarify the public artifact target: GitHub case study, website system page, portfolio note, demo companion, or README section.
- Read
references/case-study-template.mdand use its section order unless the destination already has a stronger house style. - Read
references/safety-boundary-examples.mdbefore writing the opening boundary note and final Safety Boundary section. - Extract only public-safe facts:
- Problem the system solves.
- What the system does at workflow level.
- Human review and approval points.
- General stack categories when useful.
- Outcome stated qualitatively or with approved aggregate numbers.
- What a similar client could adapt.
- Rewrite private details into generic, reusable language. Do not copy raw notes, prompts, logs, exports, database rows, or source code.
- Produce the case study in Markdown and include a short safety verdict:
BLOCK,REVIEW, orREADY.
Case Study Shape
Use these sections by default:
- Title
- Boundary note
- Public page or demo links, if already approved and live
- Problem
- What The System Does
- Workflow
- Outcome
- What Can Be Adapted For Clients
- Safety Boundary
Keep the case study short enough to scan quickly. Prefer six to eight workflow steps and three to five client-adaptation bullets.
Safety Rules
- Never include source code, private prompts, API keys, credentials, databases, logs, exports, client messages, account identifiers, local paths, or screenshots with private UI.
- Do not name clients, prospects, internal codenames, domains, or people unless the user confirms they are approved for public use.
- Use broad stack categories such as Python, SQLite, browser automation, queue dashboard, or LLM API instead of exact private architecture when details are not needed.
- Mention human approval explicitly when the system drafts, scores, publishes, sends, spends, or changes a system of record.
- If the user provides risky source material, return
BLOCKwith removal instructions before writing the publishable draft.
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 · 61 lines · 96 tokens per session scan A 50618586a39e
case-study-writer is a skill published in the GitHub repository jqaisystems/jqai-ai-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 671 once invoked, about $0.0005 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
reins
Drive the user's real, logged-in browser from the shell via the reins CLI. Because it's their actual browser, every site is already authenticated — so you can scrape behind logins, read cookies/tokens/localStorage, watch and replay live API traffic, call a site's own API as the signed-in user, and…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
skill-curator
A Chinese-language evaluator for deciding whether developer tools and agent resources are suitable for a curated collection. It checks real repositories, installation paths, activity, duplicates, and security boundaries using evidence.
git-workflow
A guide for handling Git repository work safely, including status checks, branches, commits, pushes, pull requests, and rebasing. Git is a version-control system that records code changes and coordinates work between developers.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.
review-plan
Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.