harness: Skill for Claude Code

.agents/skills/check-deps/SKILL.md

check-deps is a skill for Claude Code, Codex from boldblackai/harness. It costs 95 tokens per session (2,453 once invoked), scanned A, original, MIT.

A dependency update check for versions pinned in the project's harness Dockerfiles. Dockerfiles are instructions for building the project's container environments.

In plain words
What is it for?
Use it to check packages and tools including coding agents, GitHub CLI, cosign, uv, and pnpm, then compare pinned versions with available releases.
Why use it?
It shows whether the fixed versions used to build those environments are outdated.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: installed under .agents/ (shared by several agents); built for hermes-agent; mentions OpenCode.

This is boldblackai/harness's own configuration. It tells Claude Code and Codex how to work on harness 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 harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to boldblackai/harness. 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/boldblackai/harness/main/.agents/skills/check-deps/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/boldblackai/harness

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 check-deps

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/boldblackai/harness/check-deps"><img src="https://agentmods.dev/badge/skills/boldblackai/harness/check-deps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,453 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: 3 findings, 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 MCP Rug Pull · line 44
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
  • medium Data Exfiltration · line 52
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 92
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00095 $0.02453
Opus 5.5 $0.00038 $0.00981
Sonnet 5.5 $0.00019 $0.00491
Haiku 4.5 $0.00010 $0.00245

Measured 19d ago against content hash f00f5680dc6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

check-deps 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 19d 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.

- **GitHub releases** (`gh`, `cosign`, `uv`, `hermes-agent`, `mise`): Use the publish date from the API response (`published_at` field when using `curl -s https://api.github.com/repos/<owner/repo>/releases?per_page=5` or
.agents/skills/check-deps/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependency Version Check

This project pins nine external dependencies across its Dockerfiles. Check each one for updates and report what's current vs. what's available.

Dependencies to check

Dep File What's pinned How to find latest
@earendil-works/pi-coding-agent Dockerfile ~L56 npm version in pnpm install -g @earendil-works/pi-coding-agent@<VER> npm show @earendil-works/pi-coding-agent version
opencode-ai Dockerfile.opencode ~L6 npm version in pnpm install -g opencode-ai@<VER> npm show opencode-ai version
hermes-agent Dockerfile.hermes ~L91 git tag in --branch <TAG> gh release list --repo NousResearch/hermes-agent --limit 5
gh (GitHub CLI) Dockerfile ~L5 ARG GH_VERSION=<VER> gh release list --repo cli/cli --limit 5
cosign Dockerfile.hermes ~L12 ARG COSIGN_VERSION=<VER> gh release list --repo sigstore/cosign --limit 5
uv Dockerfile.hermes ~L10–11 ARG UV_VERSION=<VER> + ARG UV_DIGEST=sha256:... gh release list --repo astral-sh/uv --limit 5
pnpm Dockerfile ~L51 version in corepack prepare pnpm@<VER> npm show pnpm version
mise Dockerfile ~L61–65 ENV MISE_VERSION=<VER> + MISE_AMD64_SHA256 / MISE_ARM64_SHA256 checksums gh release list --repo jdx/mise --limit 5
debian:stable-slim Dockerfile L1 digest in FROM debian:stable-slim@sha256:... docker manifest inspect debian:stable-slim — see note below
uv-managed CPython Dockerfile.hermes ~L106 version in uv python install --no-cache <VER> (also passed to uv venv --python <VER>) uv python list --all-versions 3.14 — take newest 3.14.x. hermes-agent ≥ v0.21.6 gates its core deps on python_version >= '3.14' (3.11/3.13 are install bridges only, per upstream's lock comment) — the hermes image MUST track the 3.14 line.

The uv-managed CPython pin matters beyond the interpreter: python-build-standalone bundles its own SQLite, which is what hermes' _sqlite3 links at runtime. Any bump must keep the bundled SQLite at or above the minimum recorded in the Dockerfile.hermes comment near the pin (WAL-reset corruption fix line). Verify after bumping with the built image: /opt/hermes-agent/venv/bin/python3 -c "import sqlite3; print(sqlite3.sqlite_version)".

Read the full file on GitHub · 102 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. 19d ago Changed f00f5680dc6c
  2. 1mo ago Changed · +3 lines d2f19ee2eecc
  3. 2mo ago First seen · 99 lines · 95 tokens per session scan A b80cc66be169

Subscribe to this mod's changes

check-deps is a skill published in the GitHub repository boldblackai/harness (14 stars, last pushed 4d ago), licensed MIT. It adds 95 tokens to every session and 2,453 once invoked, about $0.0004 per session on Opus 5.5. 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

check-deps compared with skills from other repositories

check-deps next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
check-depsboldblackai/harnessSkill144d agoMITA95Claude Code, Codex
deploy-docker-composeomnigent-ai/omnigentSkill11kyesterdayApache-2.0A84Claude Code, Codex
bdd-container-updateNVIDIA-AI-Blueprints/video-search-and-summarizationSkill2.0kyesterdayApache-2.0A117Cursor
securing-kubernetes-on-cloudxalgorix/xalgorixSkill1.3kyesterdayApache-2.0A80Claude Code, Codex
detecting-privilege-escalation-in-kubernetes-podsxalgorix/xalgorixSkill1.3kyesterdayApache-2.0A40Claude Code, Codex
docker-socket-mountPurpleAILAB/DecepticonSkill6.5k8d agoApache-2.0B67Claude Code
k8s-networkingrohitg00/kubectl-mcp-serverSkill96815d agoMITA34Claude Code, Codex