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 skills add itallstartedwithaidea/agent-skills --skill codeql-semgrepgit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote 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/itallstartedwithaidea/agent-skills/codeql-semgrep)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/codeql-semgrep"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/codeql-semgrep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/codeql-semgrep"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/codeql-semgrep.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.01576 |
| Opus 5.5 | $0.00014 | $0.00630 |
| Sonnet 5.5 | $0.00007 | $0.00315 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
codeql-semgrep 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeQL & Semgrep
Part of Agent Skills™ by googleadsagent.ai™
Description
CodeQL & Semgrep integrates production-grade static analysis into agent workflows for deep vulnerability detection, custom rule authoring, and automated code review enforcement. The agent writes CodeQL queries and Semgrep rules tailored to project-specific patterns, runs them against codebases, and interprets results with actionable remediation guidance.
Pattern-matching security scanners catch surface-level issues. CodeQL and Semgrep operate at a deeper level: CodeQL builds a relational database of the program's structure and evaluates queries that trace data flow from sources (user input) to sinks (dangerous operations). Semgrep matches syntactic patterns with type-aware analysis. Together, they catch vulnerabilities that regex-based scanners miss entirely.
This skill goes beyond running default rulesets. The agent writes custom rules for project-specific patterns: ensuring all database queries use the project's ORM wrapper, verifying that authentication middleware is applied to every route, or confirming that error responses never leak stack traces. Custom rules encode institutional security knowledge that persists beyond any individual reviewer.
Use When
- Running static analysis on AI-generated or human-written code
- Writing custom security rules for project-specific patterns
- Integrating security scanning into CI/CD pipelines
- Tracing data flow from user input to dangerous operations
- Enforcing architectural security constraints (auth on all routes, ORM usage)
- The user requests "static analysis", "CodeQL", or "Semgrep"
How It Works
graph TD
A[Codebase] --> B{Analysis Engine}
B -->|Data Flow| C[CodeQL: Build Database]
B -->|Pattern Match| D[Semgrep: Parse AST]
C --> E[Run CodeQL Queries]
D --> F[Run Semgrep Rules]
E --> G[Taint Tracking: Source → Sink]
F --> H[Pattern Matches + Metavariables]
G --> I[Merge Findings]
H --> I
I --> J[Deduplicate + Prioritize]
J --> K[Remediation Report]
K --> L[CI/CD Gate: Pass/Fail]
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.
- 1mo ago First seen · 191 lines · 34 tokens per session scan A a6d9be1f425a
codeql-semgrep is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (44 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 1,576 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
review-stack
Stack review of one or more third-party tools (OXC, TanStack, Vite, cf, Sentry, pnpm, Claude Code...) against current official best practices, or of what a dependency bump brings (bumped): one parallel subagent per tool, verified findings, one consolidated plan in chat. USE WHEN: user runs /review-stack or explicitly…
review
Code and design review of this repo by domain - architecture, ci, code-quality, configuration, performance, security, seo, simplicity, tests, ui: one parallel reviewer subagent per selected domain, verified findings, one consolidated plan in chat with IDs to answer. USE WHEN: user runs /review, optionally with domains…
ad-delivery-review
A Chinese-language quality review and retrospective guide for advertising proposals, presentation outlines, campaign plans, strategy documents, and client pitches.
tool-defs-analysis
Read-only audit of MCP definition language across an existing surface — tools, resources, prompts, server instructions. Walks every definition file and checks 16 categories the LLM reads to decide whether and how to call: voice & tense, internal leaks, audience leaks, defaults, recovery hints, field descriptions…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
code-simplifier
Cleanup pass that edits the working tree — over a session's uncommitted changes, or a named path or whole codebase. Reads git diff (or the named target) and simplifies, consolidates, and aligns code with the existing codebase — modernize syntax, cut unnecessary complexity and slop, consolidate duplicated logic, catch…