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 tony/skills --skill case-study-internalgit clone --depth 1 https://github.com/tony/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/tony/skills/case-study-internal)<a href="https://agentmods.dev/skills/tony/skills/case-study-internal"><img src="https://agentmods.dev/badge/skills/tony/skills/case-study-internal/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/tony/skills/case-study-internal"><img src="https://agentmods.dev/badge/skills/tony/skills/case-study-internal.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 | $0.00034 | $0.00803 |
| Opus 5.5 | $0.00014 | $0.00321 |
| Sonnet 5.5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
case-study-internal 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 5d 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
86% identical to business-case-study-internal — 33 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Internal Case Study (tier 2)
Turn a run package into a narrative case study for internal
circulation: what happened, what it measured, what other teams can
take from it. The tier-2 contract is in audiences.md.
Read ../../references/interim-format.md first. It defines the run
location, the completeness gate, and the output frame. Defer these
until the gate passes:
../../references/provenance.md../../references/audiences.md: the tier-2 contract.
User arguments: $ARGUMENTS
Procedure
1. Locate the run and pass the gate
Per interim-format.md § Rendering a report. When the request names a
workflow, take the first line of runs --workflow <slug> as the run.
2. Ask for what the run package lacks
The run package holds no maintainer, no lessons, and no replication
notes, and may hold no build time. With a question tool, ask the user
once, in one batch (AskUserQuestion), for: the maintainer's role, the
build time if build-hours is not registered, what worked and what did
not, and what the team would change. Record the answers in
findings.md under a ## User-supplied context heading, with a
build time also appended to assumptions.yaml as an ESTIMATED entry
(provenance.md); then run business.py gate <run> again. Name a
person only as a role. Without a question tool, or without an answer, write
each such part as unknown with the data that would resolve it.
3. Render the case study
Write <run>/reports/case-study-internal.md as a narrative in this
fixed order:
- Situation: the team, the recurring task, why it cost enough to act on.
- What was built: the skill or workflow, its build time (tagged), and who maintains it.
- Measured outcomes: every figure tagged, denominator stated, window pinned. Include the costs: verification time, failed runs, maintenance.
- Lessons: what worked, what did not, what the team would do differently.
- How other teams can replicate: prerequisites, the expected ramp (and the excluded novelty window), and where results are likely to differ.
What ships with it
1 file 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.
- 5d ago Changed · +16 lines 1b2ee5252e78
- 8d ago Changed · -12 lines · +1 tokens per session 6c09695450c7
- 16d ago Changed · -5 lines 61463e32bcb4
- 1mo ago First seen · 81 lines · 33 tokens per session scan A 7f4da25f0b3c
case-study-internal is a skill published in the GitHub repository tony/skills (0 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 803 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to business-case-study-internal, differing in 33 lines, and is treated as a copy.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…