repo-deps

repo-deps is a skill for Claude Code, Codex from rjwalters/kicad-tools. It costs 34 tokens per session (19,890 once invoked), scanned B, original, MIT.

A dependency-maintenance tool for third-party packages and GitHub Actions, including updater policy and review of automated dependency pull requests. Third-party dependencies are software libraries or services maintained outside your project.

In plain words
What is it for?
Use it to check Dependabot or Renovate setup, review dependency update requests, and keep package and workflow dependencies current.
Why use it?
Old dependencies can miss fixes or become difficult to maintain, while automated update requests still need review for age, security relevance, testing, and merge policy.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code; installed under .agents/ (shared by several agents).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/skills/repo/scripts/repo-org-policy.py check-app --owner OWNER.

Good fit Use it to check Dependabot or Renovate setup, review dependency update requests, and keep package and workflow dependencies current.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools
agentmods
npx agentmods add skills/rjwalters/kicad-tools/repo-deps

Made for: Claude Code, Codex.

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 repo-deps

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-deps/github.svg)](https://agentmods.dev/skills/rjwalters/kicad-tools/repo-deps)
Your own site
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-deps"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-deps/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 repo-deps

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjwalters/kicad-tools/repo-deps"><img src="https://agentmods.dev/badge/skills/rjwalters/kicad-tools/repo-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 19,890 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00034 $0.19890
Opus 5.5 $0.00014 $0.07956
Sonnet 5.5 $0.00007 $0.03978
Haiku 4.5 $0.00003 $0.01989

Measured 5d ago against content hash 810d4802b5c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

repo-deps scanned grade B 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 5d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

regardless of `interval: weekly`. Never tell the user to "expect your first PR
.agents/skills/repo-deps/SKILL.md · 1,513 lines

How it starts

The opening of the file, as written. The whole thing — 1,513 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex form of the /repo:deps command. Other commands appear as $repo-<verb> skills. Helper scripts and .claude/ paths below are relative to the repository root and exist when the Claude Code surface is installed alongside this one.

$repo-deps — Third-Party Dependency Currency

Keep the repo's third-party dependencies current: npm / pip / cargo / Go packages and GitHub Actions. Two halves, usually run together:

  1. Resolve organization policy and verify the updater — Dependabot by default, Renovate only as an explicit opt-in, independently of GitHub vulnerability alerts and security PRs.
  2. Triage dependency PRs — actual changes, age eligibility, security relevance, CI coverage, and merge policy.

This is the companion to [[update-tools]], not a part of it. update-tools compares installer-managed tool packages (Loom, Anvil, Repo Skills) against a local source clone; there is no source clone to diff for Dependabot, and "triage incoming bot PRs" is a different activity from "update an installed package." Keeping them separate keeps update-tools' comparison model intact.

Everything here either writes repo config, flips a repository setting, or merges a PR — so like release, remote, followups, and update-tools, this command requires authorization for writes and merges. Apply existing authorization when it covers the concrete changes; otherwise show the changes and confirm first. --check is always report-only.

Usage

$repo-deps                  # Report policy, updater status, and open dependency PRs
$repo-deps --check          # Report only — never writes, never merges
$repo-deps --install        # Only setup reconciliation (policy + config + settings)
$repo-deps --review         # Only the PR-triage half
$repo-deps --review 123     # Triage one PR in depth
$repo-deps --all-repos               # Fan-out survey: migration state across the current repo's org, report-only
$repo-deps --all-repos --owner OWNER # Same, for an explicit org/owner

Read the full file on GitHub · 1,513 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. 5d ago Changed · +94 lines 810d4802b5c9
  2. 8d ago First seen · 1,419 lines · 34 tokens per session scan B c29e291e071f

Subscribe to this mod's changes

repo-deps is a skill published in the GitHub repository rjwalters/kicad-tools (73 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 19,890 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.

Related

repo-deps compared with skills from other repositories

repo-deps next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-depsrjwalters/kicad-toolsSkill73yesterdayMITB34Claude Code, Codex
chinese-git-workflowjnMetaCode/superpowers-zhSkill8.5k14d agoMITA69Claude Code
atmos-profilescloudposse/atmosSkill1.4ktodayApache-2.0A35Claude Code
webhook-managementhoangsonww/Claude-Code-Agent-MonitorSkill1.2kyesterdayMITA56Claude Code, Codex
deployment-engineerrmyndharis/antigravity-skillsSkill2.0k2d agoMITA73Claude Code, Codex
monorepo-managementwshobson/agentsSkill42kyesterdayMITC54Claude Code
postman-newman-automationLambdaTest/agent-skillsSkill3914d agoMITA156Claude Code, Codex