resolve-codeql

A command for finding and fixing CodeQL security alerts in the current repository. CodeQL is a code-scanning tool that detects potential vulnerabilities such as unsafe permissions or expression injection.

In plain words
What is it for?
Use it to list alerts, fix all alerts, focus on permission or injection problems, handle other alert types, or limit the work to one workflow file.
Why use it?
It organizes alerts by type, file, and batch, then routes them to specialized fixes instead of requiring each issue to be handled manually.

Command

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 commands/dryvist/claude-code-plugins/resolve-codeql
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00007 $0.01061
Opus 5 $0.00003 $0.00531
Sonnet 5 $0.00001 $0.00212
Haiku 4.5 $0.00001 $0.00106

Measured yesterday against content hash 07c3e4b96e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

resolve-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 yesterday.

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.

codeql-resolver/commands/resolve-codeql.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve CodeQL

Fix CodeQL alerts in current repository only by analyzing, classifying, and delegating to specialized agents.

Scope Options

Usage Scope Batch Size
/resolve-codeql List all alerts N/A
/resolve-codeql fix Fix all alerts 5
/resolve-codeql type:permissions Permissions alerts only 5
/resolve-codeql type:injection Expression injection only 5
/resolve-codeql type:other Other alert types 5
/resolve-codeql file:path/to/workflow.yml Specific file only N/A
  • codeql-permissions-auditor agent - Fix missing permissions
  • codeql-expression-injector agent - Mitigate injection vulnerabilities
  • codeql-generic-resolver agent - Handle other alert types
  • codeql-permission-classification skill - Permission requirements
  • github-workflow-security-patterns skill - Security patterns

Workflow

Phase 1: Alert Discovery & Classification

Replace <OWNER> and <REPO> before running.

This endpoint needs a token carrying security_events: read (App installation) or the security_events scope (classic PAT). Without it the call returns 403 Resource not accessible by integration. That is a credential gap, not an empty alert list — never read it as "no alerts". See the gh-cli-patterns skill for how to tell that 403 apart from the one meaning code scanning is simply disabled.

gh api 'repos/<OWNER>/<REPO>/code-scanning/alerts?state=open&per_page=100' --paginate \
  --jq '.[] | {
    number,
    rule: .rule.id,
    severity: .rule.severity,
    location: .most_recent_instance.location.path,
    message: .most_recent_instance.message.text
  }'

Group results by rule type:

  • actions/missing-workflow-permissions -> Permissions category
  • actions/expression-injection -> Expression injection category
  • Others -> Generic category

Apply scope filter (if provided):

  • type:permissions, type:injection, type:other
  • file:<path> - only alerts in specific file

Read the full file on GitHub · 142 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. yesterday First seen · 142 lines · 7 tokens per session scan A 07c3e4b96e4b

Subscribe to this mod's changes

resolve-codeql is a command published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 7 tokens to every session and 1,061 once invoked, about $0.0000 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 2026-08-31.