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/nishilbhave/codeprobe/codeprobe-frameworknpx skills add nishilbhave/codeprobe --skill codeprobe-frameworkgit clone --depth 1 https://github.com/nishilbhave/codeprobeWhat 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 | $0.00095 | $0.02307 |
| Opus 5 | $0.00048 | $0.01154 |
| Sonnet 5 | $0.00019 | $0.00461 |
| Haiku 4.5 | $0.00010 | $0.00231 |
Grade A, and why
codeprobe-framework 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standalone Mode
If invoked directly (not via the orchestrator), you must first:
- Read
../codeprobe/shared-preamble.md(resolve relative to this SKILL.md's location — the siblingcodeprobeskill directory — not the user's project) for the output contract, execution modes, and constraints. - Load applicable reference files from
../codeprobe/references/(same resolution) based on the project's tech stack. - Default to
fullmode unless the user specifies otherwise.
Framework-Specific Best Practices
Domain Scope
This sub-skill detects framework-specific anti-patterns and convention violations. Unlike other sub-skills that apply universal principles, this one loads framework-specific reference guides and checks against framework idioms.
Supported frameworks:
- PHP / Laravel — Eloquent ORM, routing, validation, queues, events, configuration
- React / Next.js — Component design, hooks, data fetching, type safety
- Python / Django / FastAPI — PEP conventions, ORM patterns, async handling
Important: If no supported framework is detected at the target path, emit zero findings and return an empty summary with a note: "No supported framework detected — skipping framework-specific checks."
Version Awareness: When checking framework conventions, attempt to determine the framework version:
- Laravel: check
composer.jsonforlaravel/frameworkversion. Laravel 9+ uses attribute-based accessors instead ofgetXAttribute(). - Next.js: check
next.config.*andpackage.jsonfor Next.js version. 13+ uses App Router withapp/directory. - Django: check
requirements.txtorsetup.pyfor Django version.
What It Does NOT Flag
- Issues already covered by other sub-skills even if they appear in framework code. Specifically:
- Security issues in framework code → covered by
codeprobe-security(SEC) - SOLID violations in framework classes → covered by
codeprobe-solid(SRP/OCP/etc.) - Performance issues like N+1 queries → covered by
codeprobe-performance(PERF) - Error handling in framework middleware → covered by
codeprobe-error-handling(ERR)
- Security issues in framework code → covered by
- This sub-skill focuses exclusively on framework idiom violations — using the framework incorrectly or ignoring its conventions.
- When this sub-skill and another sub-skill flag the same file:line range, the orchestrator's deduplication step (Section 7A) will keep the finding in whichever category is most relevant and mark the framework finding as a duplicate.
- Framework-generated boilerplate files (migration stubs, config defaults, scaffolded controllers).
- Intentional deviations from framework conventions with clear comments explaining the reason.
- Test files — test-specific framework usage has different conventions.
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 · 113 lines · 95 tokens per session scan A c0c2248b1bf7
codeprobe-framework is a skill published in the GitHub repository nishilbhave/codeprobe (5 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,307 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.