sq: Skill for Claude Code

.agents/skills/sq-actions-dependabot/SKILL.md

sq-actions-dependabot is a skill for Claude Code from neilotoole/sq. It costs 65 tokens per session (1,316 once invoked), scanned A, original, MIT.

A procedure for reviewing Dependabot pull requests that update GitHub Actions, the reusable tasks run by GitHub workflows. It checks version pins, comments, validation, and merge order.

In plain words
What is it for?
Use it to audit or validate GitHub Actions Dependabot pull requests, and to merge them when explicitly requested and the checks pass.
Why use it?
It separates these workflow updates from dependency updates in Go or site projects and reduces conflicts when several pull requests change the same workflow file.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is neilotoole/sq's own configuration. It tells Claude Code how to work on sq itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sq configures →

Part of the sq plugin — 4 skills shipped together

About the project

sq is a command-line data-wrangling tool that lets users query, join, inspect, compare, and transform SQL databases and structured files such as CSV and Excel using SQL or jq-like queries. It is intended for people working with databases and tabular or document data. Catalogue add-ons provide workflows for using sq from coding agents.

neilotoole/sq · 2,564 stars · on GitHub · sq.io

Reuse

Borrowing it

Nothing to install: this file belongs to neilotoole/sq. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/neilotoole/sq/master/.agents/skills/sq-actions-dependabot/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/neilotoole/sq

Made for: Claude Code.

Or install sq, the plugin that ships this one along with the rest of its 4 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 sq-actions-dependabot

README.md
[![agentmods](https://agentmods.dev/badge/skills/neilotoole/sq/sq-actions-dependabot/github.svg)](https://agentmods.dev/skills/neilotoole/sq/sq-actions-dependabot)
Your own site
<a href="https://agentmods.dev/skills/neilotoole/sq/sq-actions-dependabot"><img src="https://agentmods.dev/badge/skills/neilotoole/sq/sq-actions-dependabot/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.

agentmods 80×15 button for sq-actions-dependabot

Your own site · 80×15
<a href="https://agentmods.dev/skills/neilotoole/sq/sq-actions-dependabot"><img src="https://agentmods.dev/badge/skills/neilotoole/sq/sq-actions-dependabot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Prompt Injection · line 72
    Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
    Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
How audits are shown
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 $0.00065 $0.01316
Opus 5 $0.00032 $0.00658
Sonnet 5 $0.00013 $0.00263
Haiku 4.5 $0.00006 $0.00132

Measured yesterday against content hash ba77e0b1bcc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sq-actions-dependabot 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 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.

Makes network callslowCapability

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

# bash <(curl https://raw.githubusercontent.com/rhysd/actionlint/main/scripts/download-actionlint.bash)
.agents/skills/sq-actions-dependabot/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sq-actions-dependabot

Maintainer workflow for Dependabot PRs in the github-actions ecosystem: version bumps to uses: action pins under .github/workflows/. For go.mod / go.sum PRs use sq-gomod-dependabot; for site/ Bun/Hugo PRs use sq-site-dependabot.

Actions are pinned by full commit SHA with a trailing # vX tag comment (for example docker/login-action@650006c... # v4). Dependabot bumps the SHA and the comment together; confirm they stay in sync.

No lockfile is involved, so action PRs are loosely coupled. Two PRs can still conflict when they edit adjacent uses: lines in the same workflow file (.github/workflows/main.yml holds most pins), so merge sequentially and @dependabot rebase the next PR after each squash merge.

Operating modes

Mode Actions Merge
Audit List/classify; publisher + bump type No
Validate Diff review; CI green; actionlint No
Full Validate + merge with consent Per PR

Default to Audit unless the user asks to merge.

Phase 0 — Tool bootstrap

command -v gh >/dev/null && gh auth status
# Optional local workflow lint (CI already runs actionlint in the `lint` job):
#   bash <(curl https://raw.githubusercontent.com/rhysd/actionlint/main/scripts/download-actionlint.bash)

Phase 1 — Discovery

From repository root:

gh pr list --author 'app/dependabot' --state open \
  --json number,title,headRefName,headRefOid,mergeable,statusCheckRollup \
  --jq '.[] | select(.headRefName | test("^dependabot/github_actions/"))'

Match on headRefName, not the title. Titles such as "bump goreleaser-action" or "bump golangci-lint-action" trip the gomod skill's word filter but belong here. Confirm the diff only touches .github/workflows/ (gh pr diff <n> --name-only).

Read the full file on GitHub · 123 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 Changed ba77e0b1bcc8
  2. 12d ago First seen · 123 lines · 65 tokens per session scan A 42c04ea1dc5c

Subscribe to this mod's changes

sq-actions-dependabot is a skill published in the GitHub repository neilotoole/sq (2,564 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,316 once invoked, about $0.0003 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 2026-08-30.