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/harnessprotocol/harness-kit/dependabot-sweepnpx skills add harnessprotocol/harness-kit --skill dependabot-sweepgit clone --depth 1 https://github.com/harnessprotocol/harness-kitWrote 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.
[](https://agentmods.dev/skills/harnessprotocol/harness-kit/dependabot-sweep)<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/dependabot-sweep"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/dependabot-sweep.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00149 | $0.02348 |
| Opus 5 | $0.00075 | $0.01174 |
| Sonnet 5 | $0.00030 | $0.00470 |
| Haiku 4.5 | $0.00015 | $0.00235 |
Grade A, and why
dependabot-sweep 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 4d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependabot Sweep
Resolve open Dependabot alerts end to end: fetch → triage → fix per ecosystem → verify → branch → commit → push → PR → merge. Built to run with minimal intervention.
Announce at start: "I'm using the dependabot-sweep skill to clear open Dependabot alerts."
This is a workflow skill. It invokes the gh CLI, the repo's package managers (pnpm / npm / cargo / pip / go / bundler), git, and may hand the final merge to the merge-pr skill.
Autonomy contract
Running this skill is the user's consent for the whole workflow — fetch through merge — with no confirmation prompts. Do not ask "should I push / open a PR / merge?". Proceed.
Stop and surface a concise summary only when an Escalate condition is hit:
- A required fix is a SemVer-major bump of a direct dependency (real breaking-change risk).
- Lockfile regeneration would pull major bumps of packages unrelated to the alert (churn well beyond the targeted package and its subtree). A large minor/patch refresh of a stale lockfile is fine — note it, don't stop.
- No patched version exists, or the only remaining vulnerable copy is an upstream-pinned / build-only transitive with no reachable fix → document it and recommend dismissing that specific alert; fix everything else and continue.
- The ecosystem audit still reports the vulnerability after the fix.
- CI fails and the documented quick-fixes don't resolve it after one attempt.
- A merge conflict with the base branch that isn't a trivial lockfile re-resolution.
- A manifest uses an ecosystem with no playbook here.
When you escalate, do the fixable work first, then present only the decision the user actually needs to make.
Step 1 — Fetch open alerts
Resolve the repo, then list every open alert grouped by manifest:
REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
gh api "repos/$REPO/dependabot/alerts" --paginate \
-q '.[] | select(.state=="open")
| [.number, .security_advisory.severity, .dependency.package.ecosystem,
.dependency.package.name, .dependency.manifest_path, .dependency.scope,
.security_vulnerability.vulnerable_version_range,
.security_vulnerability.first_patched_version.identifier] | @tsv' \
| sort -t$'\t' -k5 | column -t -s$'\t'
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 183 lines · 149 tokens per session scan A 1921f4edc557
dependabot-sweep is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed today), licensed Apache-2.0. It adds 149 tokens to every session and 2,348 once invoked, about $0.0007 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
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
product-image-processor
Download, resize, and remove backgrounds from product images at scale. Use when the user asks to "process product images", batch-download images from the schedule, strip backgrounds, or standardize product photos.
tool-catalog
Show the available Architecture Studio skills and their host-appropriate commands, plus Claude Code's native Architecture Studio agents. Use when the user invokes tool-catalog, asks "what can you do" or "what skills are available", or wants a directory of plugin commands. Do not use for a host's native skill-list…
cesiumjs-imagery
CesiumJS imagery layers - ImageryProvider, ImageryLayer, ImageryLayerCollection, WMS, WMTS, Bing, OpenStreetMap, ArcGIS, Mapbox, tile discard policies. Use when adding or swapping base map layers, configuring imagery providers, layering multiple map sources, or creating split-screen imagery comparisons.
studio-feedback
Prepare a user-reviewed Architecture Studio bug report or feature request for GitHub. Use when the user runs /as:studio-feedback, says "report a bug", "this skill broke", "send feedback", or requests a feature. Do not use for Claude Code's native /feedback command.