codeql

codeql is a skill for Claude Code from ulises-jeremias/agent-toolkit. It costs 52 tokens per session (2,557 once invoked), scanned A, original, MIT.

An operational workflow for CodeQL, a tool that analyzes source code for security problems by tracing how data moves through a program. It covers setup, scans, SARIF findings, fixes, and verification.

In plain words
What is it for?
Use it to configure and run CodeQL, inspect rule and data-flow evidence, triage alerts, apply fixes, and re-run focused checks.
Why use it?
It separates semantic security analysis from broad linting, making vulnerability findings easier to investigate and confirm.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-toolkit-complete plugin — 116 skills shipped together

Good fit Use it to configure and run CodeQL, inspect rule and data-flow evidence…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ulises-jeremias/agent-toolkit/codeql
Install

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.

Any agent
npx skills add ulises-jeremias/agent-toolkit --skill codeql
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

Made for: Claude Code.

Or install agent-toolkit-complete, the plugin that ships this one along with the rest of its 116 skills.

Wrote 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.

agentmods badge for codeql

README.md
[![agentmods](https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/codeql.svg)](https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/codeql)
Your own site
<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/codeql"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/codeql.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02557
Opus 5 $0.00026 $0.01278
Sonnet 5 $0.00010 $0.00511
Haiku 4.5 $0.00005 $0.00256

Measured 7d ago against content hash cad085cedc79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 7d 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.

plugins/agent-toolkit-complete/.github/skills/codeql/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeQL — Operational Security Analysis Workflow

Help coding agents operate CodeQL, not just explain syntax. Covers discovery of existing setup, config review, scan execution/inspection, SARIF triage with evidence discipline, remediation, and targeted re-validation.

Sources: GitHub Docs Code Scanning with CodeQL (2026-08-12, https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/about-code-scanning-with-codeql), CodeQL CLI (github/codeql MIT, CLI binaries separate), github/codeql-action (https://github.com/github/codeql-action), and this repo's .github/workflows/codeql.yml (Analyze Python via codeql-action/init@v4 + analyze@v4).

Relationship to MegaLinter:

  • MegaLinter: broad linting/formatting/static quality orchestration (50+ linters, Docker-based, .mega-linter.yml, fast feedback on style, config, IaC).
  • CodeQL: semantic security analysis / dataflow / vulnerability classes (source→sink taint, e.g., python/sql-injection, js/xss, SARIF alerts).
  • Neither replaces the other. Composition: code-quality / secure-delivery → { MegaLinter, CodeQL } without a giant orchestrator.

When to use

  • Repo has or needs CodeQL code scanning (.github/workflows/codeql.yml, codeql-action, SARIF alerts)
  • Need to triage a CodeQL alert (security tab, SARIF file, CI log) with evidence
  • Need to fix a finding and re-validate
  • Workflow failing (timeout, OOM, build failure for compiled languages, config error)
  • Need custom query / query-pack guidance (when to write vs reuse)

Modes (one skill, contextual)

Mode Trigger What it does
SETUP / CONFIG REVIEW No CodeQL workflow, or outdated codeql-action version, or new language to add Inspect .github/workflows/codeql.yml, languages:, queries:, paths:, paths-ignore:, schedule, permissions (security-events: write); recommend init@v4/analyze@v4 (or codeql-action latest), language matrix, build-mode for compiled (manual/autobuild/none)
FINDING TRIAGE SARIF file, alert URL, or Run CodeQL log with failure Parse SARIF (runs[].tool.driver.rules[], runs[].results[]), map ruleId → query help, extract locations[0].physicalLocation, codeFlows (source→sink), message.text, level/category, partialFingerprints; produce evidence table
REMEDIATION Triaged finding with fix needed Propose minimal fix (sanitize, parameterized query, escape), show diff, reference query docs, note confidence/severity, and how to suppress via // lgtm[…] or codeql-config.yml only when justified (ask before suppress)
WORKFLOW TROUBLESHOOTING analyze job failed, no alerts, or out of memory Check codeql-action logs, AUTOBUILD vs manual build, ram: / threads:, debug: true, upload-sarif fallback, category duplication
CUSTOM QUERY Need to detect a repo-specific pattern beyond standard packs Guide when to reuse security-and-quality vs security-extended vs write custom QL (pack codeql/<lang>-queries), use codeql pack create + codeql query run locally, test with codeql test run

Read the full file on GitHub · 107 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 7d ago First seen · 107 lines · 52 tokens per session scan A cad085cedc79

Subscribe to this mod's changes

codeql is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 2,557 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

verify

Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.

yha9806/academic-writing-toolkit · 26 tokens

iblai-api-catalog-media

Manage an ibl.ai organization's catalog media resources via the Data Manager API — videos, images, documents, audio, and external links attached to a course, unit, or resource (item). Per-org, per-user CRUD plus search and by-item lookup, with multipart file upload. Use when attaching media to course/unit/resource…

iblai/api · 88 tokens

iblai-api-agent-skill

Manage an ibl.ai agent's skills via the platform API — browse the org skill catalog, assign/unassign skills to an agent, and create/edit/delete catalog skills. Requires a connected sandbox. Use when giving an agent reusable skill instructions.

iblai/api · 55 tokens

iblai-api-agent-safety

Configure an ibl.ai agent's moderation and safety systems via the platform API — enable flags, system prompts and responses (saved through the agent settings endpoint) — and review or delete flagged-prompt moderation logs. Use when setting guardrails or auditing flagged content.

iblai/api · 59 tokens

iblai-api-agent-disclaimer

Manage an ibl.ai agent's disclaimers via the platform API — the Advisory text (saved through the agent settings endpoint) and the User Agreement (create/update/activate). Use when adding legal or advisory notices users must see or accept.

iblai/api · 55 tokens

pr-alignment-loop

Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…

nikships/skills-registry · 122 tokens