Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Sassy-Dog/sassydog-skills/plugin install sassy-dogWrote 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/sassy-dog/sassydog-skills/setup-deps)<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/setup-deps"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/setup-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.
<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/setup-deps"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/setup-deps.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00178 | $0.06705 |
| Opus 5 | $0.00089 | $0.03352 |
| Sonnet 5 | $0.00036 | $0.01341 |
| Haiku 4.5 | $0.00018 | $0.00671 |
Grade A, and why
setup-deps 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 6d 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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Deps
Generator/refresher for a repo's dependency automation, in the same family as
setup-config and setup-hooks: detect the stack, render from templates,
reconcile only what this generator owns.
It renders up to three things:
| File | When |
|---|---|
.github/dependabot.yml |
always — grouped, one entry per (ecosystem, directory) |
.github/workflows/dependabot-auto-merge.yml |
when the repo has a merge gate AND is not public — two preconditions, see §2 |
.github/workflows/dependabot-bun-lockfile.yml |
legacy fallback — only when npm has lockfile_risk (binary bun.lockb, or a repo deliberately on npm + sync) AND the repo is not public; a text bun.lock renders the native bun ecosystem instead, no sync workflow. One per bun install root, not one per repo |
.github/workflows/dependabot-pod-lockfile.yml |
when cocoapods is detected and the app's ios/Podfile.lock is tracked (see §3) AND the repo is not public |
Bundled scripts (scripts/): detect-ecosystems.sh (probe), render-dependabot.sh (render),
validate-dependabot.sh (post-render assertion + divergence check), and lib-ecosystems.sh — the
one ecosystem table all three read, so the validator can never agree with a renderer that is wrong.
Ownership marker: the generated-by: comment on the first non-blank line after the YAML document
start. Re-runs reconcile only files carrying that marker — a hand-written dependabot.yml is
reported and left alone, never overwritten.
Ownership matching is deliberately wide: accept EITHER marker namespace — the current
sassy-dog: prefix and the pre-rename ai-agent-skills: prefix (plugin ≤ 2026.8.20) — paired
with ANY producer name this generator has ever emitted: setup-deps (current), refresh-deps
(plugin ≤ 2026.8.39), and refresh-sassydog-deps (plugin ≤ 2026.7.21). A file is owned when its
marker matches:
generated-by: (sassy-dog|ai-agent-skills):(setup-deps|refresh-deps|refresh-sassydog-deps)
All six namespace × producer-name combinations are owned. The plugin rename moved the namespace
before the colon; the two generator renames moved the name after it. This matters more here than
almost anywhere else in the plugin: the marker is committed inside every consumer repo, in
.github/dependabot.yml and each dependency workflow, so a matcher narrowed to the current
producer name would classify every pre-rename file as hand-written and refuse to reconcile it —
and it would fail silently, because the contract above is report-and-skip, not error.
Normalise the marker to the current sassy-dog:setup-deps form on write (expect a one-line
diff per file on a pre-rename repo's first re-run; that is the intended outcome, not drift).
What ships with it
8 files 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.
- references/templates/dependabot-auto-merge.template.yml 5.8 KB
- references/templates/dependabot.yml.template 9.4 KB
- references/templates/lockfile-sync-bun.template.yml 12 KB
- references/templates/lockfile-sync-pod.template.yml 8.1 KB
- scripts/detect-ecosystems.sh 12 KB runs code
- scripts/lib-ecosystems.sh 9.9 KB runs code
- scripts/render-dependabot.sh 5.7 KB runs code
- scripts/validate-dependabot.sh 9.7 KB runs code
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.
- 6d ago Changed · +17 lines 2f02d1eb8e44
- 10d ago First seen · 382 lines · 178 tokens per session scan A 20ae73c3f5bf
setup-deps is a skill published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 178 tokens to every session and 6,705 once invoked, about $0.0009 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
setup-solution
Creates a Dataverse publisher and solution, then adds Power Pages site components to the solution for ALM and deployment management. Use when asked to: "create solution", "set up solution", "add to solution", "package site into solution", "create publisher", "solutionize my site", or "set up ALM for my site".
setup-pipeline
Sets up a Power Platform Pipeline for automated Power Pages deployments. Power Platform Pipelines is Microsoft's native CI/CD tool built into the Power Platform — no external infrastructure required. Use when asked to: "set up ci/cd", "create pipeline", "setup pipeline", "set up power platform pipelines", "create…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
force-link-environment
Force-links a development or target environment to a Power Platform Pipelines host, overriding any existing association with a previous host. Use when creating a deploymentenvironments record fails with "this environment is already associated with another pipelines host", or when intentionally migrating an environment…
add-azuredevops
Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API calls.
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.