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/bostonorange/claude-code-framework/generate-internal-appnpx skills add BostonOrange/claude-code-framework --skill generate-internal-appgit clone --depth 1 https://github.com/BostonOrange/claude-code-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 | $0.00018 | $0.00854 |
| Opus 5 | $0.00009 | $0.00427 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
generate-internal-app 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Internal App
Consume an app blueprint and modify the internal Next.js business app template into a working business application. This skill owns orchestration and code generation steps; keep the app's core architecture inside the app template.
Usage
/generate-internal-app docs/app-blueprint.json
/generate-internal-app docs/app-blueprint.json --feature invoice-approval
If no blueprint path is provided, look for docs/app-blueprint.json. If it is missing, run /app-blueprint first.
Preconditions
The target repo should contain the internal app preset:
package.jsonprisma/schema.prismasrc/app/apisrc/lib/db/prisma.tssrc/lib/blob/client.tssrc/lib/auth
If these are missing, stop and tell the user to re-run setup with the "Internal Next.js Business App" preset.
Process
- Validate the blueprint JSON.
- Ensure
appName,usersAndRoles,entities,workflows,permissions,filesBlobNeeds,auditEvents,dashboardsViews, andaiAssistPointsexist. - Report open questions that block safe generation.
- Ensure
- Plan the generation slice.
- Full app: generate all core entities and views.
- Feature mode: generate only the requested workflow/entity slice and do not churn unrelated files.
- Update Prisma.
- Add enums for entity statuses and role/action concepts where useful.
- Add models for blueprint entities.
- Keep
User,FileObject, andAuditLogunless the blueprint explicitly replaces them. - Prefer relational foreign keys over denormalized JSON for workflow state.
- Generate repository modules under
src/lib/<entity>/repository.ts.- Keep Prisma calls inside repositories.
- Return plain domain objects to routes/pages.
- Add create/update/status-transition helpers matching workflows.
- Generate API routes under
src/app/api/<entity>/route.tsand focused subroutes when needed.- Use auth helpers from
src/lib/auth. - Validate input with Zod.
- Create audit events for every workflow transition.
- Keep blob operations behind
src/lib/blob/client.ts.
- Use auth helpers from
- Generate dashboard UI.
- Add queue/table/detail/form views from
dashboardsViews. - Keep operational density appropriate for internal tools.
- Include file upload controls only where
filesBlobNeedsrequires them.
- Add queue/table/detail/form views from
- Update seed data in
prisma/seed.ts.- Seed users/roles and a small synthetic sample for each generated workflow.
- Never use real PII.
- Add tests where the app has a test harness.
- If no harness exists, add a short
docs/stories/<feature>/how-to-test.mdwith manual and typecheck validation.
- If no harness exists, add a short
- Update docs.
README.md: app-specific quick start and core workflows.docs/setup.md: provider notes only when generation changes env needs.docs/stories/<feature>/: generated story, solution components, how-to-test, manual steps.
- Run validation.
npm run typechecknpm run lintnpm run buildwhen dependencies and env are available.
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 · 95 lines · 18 tokens per session scan A 5a5009dd1fff
generate-internal-app is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 854 once invoked, about $0.0001 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…