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/craftos-dev/craftbot/codeqlnpx skills add CraftOS-dev/CraftBot --skill codeqlgit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWhat 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 | $0.00102 | $0.03578 |
| Opus 5 | $0.00051 | $0.01789 |
| Sonnet 5 | $0.00020 | $0.00716 |
| Haiku 4.5 | $0.00010 | $0.00358 |
Grade A, and why
codeql 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.
This is a copy
89% identical to codeql — 12 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeQL Analysis
Supported languages: Python, JavaScript/TypeScript, Go, Java/Kotlin, C/C++, C#, Ruby, Swift.
Skill resources: Reference files and templates are located at {baseDir}/references/ and {baseDir}/workflows/.
Essential Principles
-
Database quality is non-negotiable. A database that builds is not automatically good. Always run quality assessment (file counts, baseline LoC, extractor errors) and compare against expected source files. A cached build produces zero useful extraction.
-
Data extensions catch what CodeQL misses. Even projects using standard frameworks (Django, Spring, Express) have custom wrappers around database calls, request parsing, or shell execution. Skipping the create-data-extensions workflow means missing vulnerabilities in project-specific code paths.
-
Explicit suite references prevent silent query dropping. Never pass pack names directly to
codeql database analyze— each pack'sdefaultSuiteFileapplies hidden filters that can produce zero results. Always generate a custom.qlssuite file. -
Zero findings needs investigation, not celebration. Zero results can indicate poor database quality, missing models, wrong query packs, or silent suite filtering. Investigate before reporting clean.
-
macOS Apple Silicon requires workarounds for compiled languages. Exit code 137 is
arm64e/arm64mismatch, not a build failure. Try Homebrew arm64 tools or Rosetta before falling back tobuild-mode=none. -
Follow workflows step by step. Once a workflow is selected, execute it step by step without skipping phases. Each phase gates the next — skipping quality assessment or data extensions leads to incomplete analysis.
Output Directory
All generated files (database, build logs, diagnostics, extensions, results) are stored in a single output directory.
- If the user specifies an output directory in their prompt, use it as
OUTPUT_DIR. - If not specified, default to
./static_analysis_codeql_1. If that already exists, increment to_2,_3, etc.
What ships with it
15 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.
- references/build-fixes.md 2.6 KB
- references/diagnostic-query-templates.md 9.8 KB
- references/extension-yaml-format.md 7.7 KB
- references/important-only-suite.md 5.6 KB
- references/language-details.md 5.0 KB
- references/macos-arm64e-workaround.md 6.7 KB
- references/performance-tuning.md 3.3 KB
- references/quality-assessment.md 6.8 KB
- references/ruleset-catalog.md 2.1 KB
- references/run-all-suite.md 4.2 KB
- references/sarif-processing.md 3.0 KB
- references/threat-models.md 3.0 KB
- workflows/build-database.md 9.4 KB
- workflows/create-data-extensions.md 9.7 KB
- workflows/run-analysis.md 11 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.
- 2d ago First seen · 270 lines · 102 tokens per session scan A b88b4f0b2044
codeql is a skill published in the GitHub repository CraftOS-dev/CraftBot (376 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 3,578 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to codeql, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
agent-smoke-test
Run manual development checks for SwiftAutoGUI AI Agent actions through the local sagui CLI. Use when Claude or Codex needs to test app-control or Accessibility BasicAction generation on macOS.
macos-control
Control macOS GUI applications via mouse automation, keyboard input, screenshots, image recognition, and AppleScript execution. Use when you need to interact with macOS app UIs, take screenshots, click buttons, type text, scroll, drag, or locate images on screen.
open-record-replay
Record a user-demonstrated macOS workflow with the Open Record/Replay CLI, inspect the captured event stream, prepare a skill evidence package, and hand it to the host agent's native skill creator. Use when the user asks the agent to watch them perform a task, record a workflow, or create/refine a reusable Computer…
artifact-storage-policy
管理 Codex 交付物的專案識別、Google Drive/GitHub 路由、檔名、儲存位置與回讀驗證;凡工作報告、外部保存、交付成果或新 repository 選擇涉及遠端儲存時使用。.