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-securitynpx skills add nishilbhave/codeprobe --skill codeprobe-securitygit 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 | $0.00078 | $0.02937 |
| Opus 5 | $0.00039 | $0.01469 |
| Sonnet 5 | $0.00016 | $0.00587 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
codeprobe-security scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `SEC` | Shell command construction with unsanitized input | Search for `exec()`, `system()`, `shell_exec()`, `popen()`, `subprocess.call()`, `subprocess.run()`, `child_process.exec()`, backtick operators. Flag when the How it starts
The opening of the file, as written. The whole thing — 137 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.
Security Vulnerability Scanner
Domain Scope
This sub-skill detects security vulnerabilities across these categories:
- Injection — SQL injection, command injection, LDAP/NoSQL injection
- Authentication & Authorization — Missing auth, weak credentials, hardcoded secrets, JWT issues
- Cross-Site Scripting (XSS) — Unescaped output, dangerous HTML rendering
- Mass Assignment — Unprotected model attribute assignment
- Cross-Site Request Forgery (CSRF) — Missing tokens, unprotected state-changing routes
- Insecure Deserialization — Unsafe deserialization of untrusted data
- Sensitive Data Exposure — Secrets in logs, committed .env files, leaked stack traces
- Broken Access Control — IDOR, missing policy/gate checks
- Security Misconfiguration — Debug mode in production, permissive CORS, default credentials
What It Does NOT Flag
- Internal admin tools with IP-restricted access — these have a different threat model and the restriction may be intentional.
- Test files using hardcoded values — test fixtures with fake credentials, tokens, and API keys are expected and appropriate.
- Development-only configuration files clearly marked as such (e.g.,
.env.example,docker-compose.dev.yml, files intests/fixtures/). - Dependencies with known CVEs — this sub-skill analyzes source code, not dependency manifests. Use dedicated tools (e.g.,
npm audit,composer audit) for dependency scanning.
Detection Instructions
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 · 137 lines · 78 tokens per session scan A 93e9272adf08
codeprobe-security is a skill published in the GitHub repository nishilbhave/codeprobe (5 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,937 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…