CodeQL Permissions Auditor

An agent that reviews CodeQL security alerts in GitHub Actions workflows. CodeQL is GitHub's tool for finding security problems in code and automation files.

In plain words
What is it for?
It is for fixing workflow permission alerts, including jobs that call reusable workflows or use actions such as checkout, pull requests, or issues.
Why use it?
It helps identify which permissions a workflow job needs and add explicit limits, reducing overly broad access.

Agent

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.

agentmods
npx agentmods add agents/dryvist/claude-code-plugins/codeql-permissions-auditor
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00012 $0.01324
Opus 5 $0.00006 $0.00662
Sonnet 5 $0.00002 $0.00265
Haiku 4.5 $0.00001 $0.00132

Measured 2d ago against content hash 756518f6d538, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CodeQL Permissions Auditor 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

3. Script operations (curl, git commands) -> Usually `contents: read`
codeql-resolver/agents/codeql-permissions-auditor.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeQL Permissions Auditor

Fix "Workflow does not contain permissions" CodeQL alerts by analyzing and adding explicit permission blocks to GitHub Actions jobs.

Input

{
  "alerts": [
    {
      "number": 1,
      "location": ".github/workflows/ci-gate.yml",
      "line_number": 103,
      "message": "Actions job or workflow does not limit the permissions..."
    }
  ],
  "batch_size": 5
}

Workflow per Alert

1. Parse Alert Context

  • Extract workflow file path and approximate line number
  • Open the file and identify the job that needs fixing
  • Check if job calls reusable workflow (uses: ./.github/workflows/...) or runs steps

2. Analyze Permission Requirements

For reusable workflow calls:

  • Read the called workflow file (e.g., ./.github/workflows/_cclint.yml)
  • Extract all jobs within and their permission blocks
  • Union all permissions from nested jobs
  • Apply caller contract rule: "Caller must declare permissions for all jobs in callee"

For regular step jobs:

  • Scan steps for which actions/tools are used
  • Map each to required permissions:
    • actions/checkout -> contents: read
    • pull-requests operations -> pull-requests: write
    • issues operations -> issues: write
    • artifact operations -> actions: read or contents: read
    • Custom actions -> Inspect action.yml for required permissions

3. Determine Minimum Permissions

Apply hierarchy:

  1. Explicit permissions in reusable workflow -> Required
  2. GitHub actions used in steps -> Required
  3. Script operations (curl, git commands) -> Usually contents: read
  4. No operations at all -> Empty permissions: {}

4. Apply Fix

Edit the workflow file:

job-name:
  name: Display Name
  needs: changes                    # Original
  if: condition                     # Original
  permissions:                      # ← ADD THIS
    contents: read                  # Minimum
    pull-requests: write            # If needed
  uses: ./.github/workflows/_.yml   # Original
  with:                             # Original
    ...

Read the full file on GitHub · 202 lines

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. 2d ago First seen · 202 lines · 12 tokens per session scan A 756518f6d538

Subscribe to this mod's changes

CodeQL Permissions Auditor is an agent published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,324 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

thoughts-analyzer

Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…

hoblin/claude-ruby-marketplace · 61 tokens

documentation-researcher

Need to learn how to use a library, gem, or framework? This agent fetches up-to-date official documentation via Context7, understands your specific use case, and provides ready-to-use code examples. Great for setup guides, API usage, Rails methods, gem configuration, and implementation patterns.

hoblin/claude-ruby-marketplace · 64 tokens

swarm-worker

Execute a single swarm task in an isolated git worktree. Receive a fully-specified recipe from the main context — a scenario recipe plus an implementation contract — then run Skill(scenario) followed by Skill(implement) and report JSON status. Make no design decisions and do not expand scope. Invoked exclusively by…

friedbotstudio/baseline · 77 tokens

assistente-migracao

Especialista em migração de dados para a Tray. Utilize quando precisar migrar dados de outras plataformas de e-commerce (Shopify, WooCommerce, Magento, VTEX, Nuvemshop, etc.) para a Tray, incluindo produtos, clientes, pedidos e categorias.

tray-tecnologia/tray-api-ai-plugin · 61 tokens

platform-engineer

Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.

ulises-jeremias/agent-toolkit · 88 tokens

review-rails

Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.

hoblin/claude-ruby-marketplace · 64 tokens