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/ai-driven-dev/framework/use-casenpx skills add ai-driven-dev/framework --skill use-casegit clone --depth 1 https://github.com/ai-driven-dev/frameworkWhat 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 | $0.00096 | $0.00635 |
| Opus 5 | $0.00048 | $0.00318 |
| Sonnet 5 | $0.00019 | $0.00127 |
| Haiku 4.5 | $0.00010 | $0.00064 |
Grade A, and why
use-case 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Case
Builds the business orchestration layer: classes that receive typed options, coordinate ports and
domain models, and return typed results. Each use-case has a single execute() method, never
catches its own errors, and delegates all file-and-manifest writes to PostInstallPipelineUseCase.
Available actions
| # | Action | Role | Input |
|---|---|---|---|
| 01 | define-types |
Declare *Options and *Result interfaces |
use-case name + field list |
| 02 | write-execute |
Write the execute() method body (≤20 LOC) |
types from 01 |
| 03 | extract-methods |
Extract intent-named private helper methods | execute() body from 02 |
| 04 | wire-errors-and-pipeline |
Add typed throws + delegate to PostInstallPipeline | methods from 03 |
| 05 | test |
Write integration-tier unit tests | completed use-case from 04 |
Default flow
01 → 02 → 03 → 04 → 05
Transversal rules
- Class name ends in
UseCase; singleasync execute()method; never a plain function. - Every method (public or private) ≤ 20 lines; extract named private methods before reaching the limit.
- Shared sub-use-cases live in
src/application/use-cases/shared/and are never called from commands. - Capability sub-use-cases live in subdirectories (
install/,update/) and receive narrowed types. - Never call
manifestRepo.save()in isolation; delegate toPostInstallPipelineUseCase. - Use constructor injection order: FileSystem → Repository → Loader → Hasher → Logger → Platform → Prompter.
- Use
import typefor type-only imports;.jsextensions on all relative imports. - Named export only.
References
references/use-case-rules.md— class shape, constructor order, Prompter restrictions, user-file protectionreferences/shared-use-cases.md— shared sub-use-case placement and contractreferences/capability-sub-use-cases.md— capability guard pattern, narrowed typesreferences/post-install-pipeline.md— pipeline delegation rules
What ships with it
11 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.
- actions/01-define-types.md 1.3 KB
- actions/02-write-execute.md 1.8 KB
- actions/03-extract-methods.md 1.5 KB
- actions/04-wire-errors-and-pipeline.md 1.5 KB
- actions/05-test.md 1.4 KB
- evals/scenarios.json 730 B
- references/bug-empirical-reproduction.md 1.0 KB
- references/capability-sub-use-cases.md 1.6 KB
- references/post-install-pipeline.md 939 B
- references/shared-use-cases.md 1018 B
- references/use-case-rules.md 4.1 KB
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 · 52 lines · 96 tokens per session scan A 89ad61086f5c
use-case is a skill published in the GitHub repository ai-driven-dev/framework (445 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 635 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 2026-08-30.
Other skills, from other repositories
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
github-deep-research
Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams.…
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.