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 skills add Sassy-Dog/sassydog-skills --skill setup-repogit clone --depth 1 https://github.com/Sassy-Dog/sassydog-skillsWrote 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-repo)<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/setup-repo"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/setup-repo/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-repo"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/setup-repo.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 | $0.00177 | $0.01927 |
| Opus 5 | $0.00088 | $0.00963 |
| Sonnet 5 | $0.00035 | $0.00385 |
| Haiku 4.5 | $0.00018 | $0.00193 |
Grade A, and why
setup-repo 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 9d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Repo
The umbrella entry point for the generator family. "Set up this repo" is three jobs, not one:
| Order | Generator | Owns |
|---|---|---|
| 1 | sassy-dog:setup-config |
.claude/sassy-dog/*.md workflow config + the .claude/settings.json marketplace/plugin declaration |
| 2 | sassy-dog:setup-hooks |
.claude/hooks/sassydog-*.sh + their .claude/settings.json hook entries |
| 3 | sassy-dog:setup-deps |
.github/dependabot.yml + the dependency automation workflows |
This skill contains no generation logic. Detection, mode selection, ownership markers, rendering and content previews all live in the three generators. A bug in any of that is fixed in the generator, never here. This skill decides only which generators run, in what order, and what the run report says.
The trigger description above owns the broad intent ALONE, and that scope is deliberate. Each of the three generators keeps its own specific vocabulary — "set up hooks for this repo", "add dependabot config here", "configure survey-work for this repo" — and a description here that swallowed those phrasings would make the specific invocations ambiguous: a user who names one area would land on the umbrella and get a three-generator plan they did not ask for. Broadening this description is the trigger-phrase tightening to refuse.
Why the orchestrator exists
The gap is invisible. A repo reached through one generator alone is a third of a setup, and nothing reports the other two-thirds as missing — it surfaces later as a routine that silently loads no skill, or a Dependabot flood nobody automated. Naming all three in one report is the whole point.
The shared write. setup-config and setup-hooks both write .claude/settings.json — config
writes extraKnownMarketplaces + enabledPlugins, hooks writes the hooks.PostToolUse entry.
Each documents a surgical merge into its own keys, never a rewrite, so sequential runs
compose: the second reads the file as the first left it and adds to it. Run them concurrently — or
let either plan against one copy and write back a whole file later — and one of the two
declarations vanishes with no error anywhere, because both generators' contracts are
report-and-skip, not fail. A prior migration lost a consumer's PreToolUse push guard to exactly
this class of settings overwrite.
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.
- 9d ago Changed · +7 lines eefdb9114b0b
- 12d ago First seen · 154 lines · 177 tokens per session scan A d4a21cb331d0
setup-repo is a skill published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 177 tokens to every session and 1,927 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
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.
push-ci
Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh CLI. Use when: user says 'push', 'push and watch CI', 'ship it', 'push-ci'. Not for: committing (use /smart-commit), creating PRs (use /create-pr), merging (use /merge-prep).
cloudflare-workers-ci-cd
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
ops-ship
OPS on-demand: This skill should be used when the user asks to "ship ops plugin", "merge all PRs and…
pipeline-digest
Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is green, and which branches went stale, and notifies the operator only when that state actually moved since the last run. Use when the operator asks "what moved in the pipeline", "anything to ship"…
babysit
PR babysitter: monitors CI status, auto-rebases when behind, auto-fixes CI where possible, delegates review comment handling to dlc:pr-check, and re-requests review after fixes. Designed for /loop usage with Remote Control.