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/dryvist/claude-code-plugins/codeql-permission-classificationnpx skills add dryvist/claude-code-plugins --skill codeql-permission-classificationgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat 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 | $0.00013 | $0.01864 |
| Opus 5 | $0.00006 | $0.00932 |
| Sonnet 5 | $0.00003 | $0.00373 |
| Haiku 4.5 | $0.00001 | $0.00186 |
Grade A, and why
codeql-permission-classification 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 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.
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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeQL Permission Classification
Single source of truth for GitHub Actions permission requirements.
Permission Types
GitHub Actions provides these permission scopes:
contents # Read/write repository content (checkout, tags, releases)
pull-requests # Read/write PR comments, reviews, assignments
issues # Read/write issue comments, labels, projects
deployments # Read/write deployment status
packages # Read/write packages
actions # Read/write GitHub Actions (runners, artifacts, caches)
checks # Read/write check runs and annotations
statuses # Read/write commit statuses
security-events # Read/write code scanning and secret scanning results
Common Actions → Permissions Matrix
| Action | Required Permissions | Use Case |
|---|---|---|
actions/checkout@v6 |
contents: read |
Clone repository |
actions/upload-artifact@v6 |
None (usually) | Store build artifacts |
actions/download-artifact@v6 |
None (usually) | Retrieve artifacts |
actions/setup-node@v6 |
None | Install Node.js |
actions/github-script@v6 |
Depends on script | Usually contents: read minimum |
actions/create-release@v1 |
contents: write |
Create GitHub release |
github/codeql-action/upload-sarif@v2 |
security-events: write |
Upload CodeQL results |
Decision Tree
Q1: Does your job use actions/checkout?
- YES → Add
contents: read - NO → Continue to Q2
Q2: Does your job modify repository (create PR, tag, release)?
- YES → Add
contents: write - NO → Continue to Q3
Q3: Does your job post comments to PR or issues?
- YES → Add
pull-requests: write(PR) orissues: write(issues) - NO → Continue to Q4
Q4: Does your job modify deployments?
- YES → Add
deployments: write - NO → Continue to Q5
Q5: Does your job use github.rest API?
- YES → Add permission for the API endpoint you're calling
- NO → Continue to Q6
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.
- 2d ago First seen · 298 lines · 13 tokens per session scan A c719c8d969ef
codeql-permission-classification is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,864 once invoked, about $0.0001 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.
Other skills, from other repositories
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
deploy-steward
Mainline deploy steward. Consumes ready PRs, owns a lease on mainline landing, refreshes PR state, updates stale branches, waits for CI and deploy gates, merges or queues one candidate at a time, and opens repair tasks for failures.
github-actions-pat
用 Personal Access Token 通过 GitHub REST API 分析 Actions CI 的失败 run/job/step、拉取日志、轮询运行状态、做 PR code review，并驱动 fix → push → watch → iterate 的闭环。Token 只从 GITHUBTOKEN 环境变量读取，不落盘、不回显。适合在 bifrost remote / CI 调度器 / 无头环境里跑。仓库锁定在 AGENTS.md 或调用处通过 GHREPO 显式指定。.
prepare-release
End-to-end release automation — reads commits since last tag, infers semver bump, drafts changelog, creates release PR, merges it, waits for CI green, tags, and monitors the Docker build to completion. Use when the user says: prepare release, cut a release, bump version, create release PR, ship a new version, tag a…
fix-ci
Investigate and fix the latest failing CI workflow.
aws-solution-architect
Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS costs, set up CI/CD pipelines, or migrate to AWS. Covers Lambda, API Gateway, DynamoDB, ECS, Aurora, and cost optimization.