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/kunanonj/ai-skills-hub/codeqlnpx skills add KunanonJ/ai-skills-hub --skill codeqlgit clone --depth 1 https://github.com/KunanonJ/ai-skills-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kunanonj/ai-skills-hub/codeql)<a href="https://agentmods.dev/skills/kunanonj/ai-skills-hub/codeql"><img src="https://agentmods.dev/badge/skills/kunanonj/ai-skills-hub/codeql.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $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 5d 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
17 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.
- agents/openai.yaml 128 B
- assets/trail-of-bits-mark.svg 3.0 KB
- 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.
- 5d ago First seen · 270 lines · 102 tokens per session scan A b88b4f0b2044
codeql is a skill published in the GitHub repository KunanonJ/ai-skills-hub (4 stars, last pushed 1mo 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
agent-creator
Create and configure AiderDesk agent profiles by defining tool groups, approval rules, system prompts, subagent settings, subagent filtering, and provider/model selection. Use when setting up a new agent, creating a profile, or configuring agent tools, permissions, and subagent behavior.
doncheli-tech-panel
Convene a senior engineering expert panel to evaluate technical decisions. Activate when user mentions "tech panel", "technical discussion", "expert opinion", "architecture decision", "which technology", "should we use".
doncheli-migrate
Plan and execute technology migrations with wave planning, breaking change detection and task generation. Activate when user mentions "migrate", "migration", "upgrade", "move from", "switch to", "Vue to React", "JS to TS", "v1 to v2".
doncheli-pr-review
Perform a structured code review of a pull request aligned with SDD principles. Activate when user mentions "PR review", "pull request", "review PR", "code review", "review this diff".
doncheli-tea
Run the full autonomous test suite end-to-end and report results. Activate when user mentions "test end to end", "autonomous testing", "run all tests", "full test run", "E2E tests", "test suite".
doncheli-webhook
Configure and test webhooks and automation triggers for the project. Activate when user mentions "webhook", "trigger", "automation", "event hook", "notify on", "callback URL".