Borrowing it
Nothing to install: this file belongs to umbraco/Umbraco.Automate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/umbraco/Umbraco.Automate/v18/dev/.claude/skills/ops-workspace/SKILL.mdgit clone --depth 1 https://github.com/umbraco/Umbraco.AutomateWrote 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/umbraco/umbraco.automate/ops-workspace)<a href="https://agentmods.dev/skills/umbraco/umbraco.automate/ops-workspace"><img src="https://agentmods.dev/badge/skills/umbraco/umbraco.automate/ops-workspace/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/umbraco/umbraco.automate/ops-workspace"><img src="https://agentmods.dev/badge/skills/umbraco/umbraco.automate/ops-workspace.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 | $0.00088 | $0.01918 |
| Opus 5 | $0.00044 | $0.00959 |
| Sonnet 5 | $0.00018 | $0.00384 |
| Haiku 4.5 | $0.00009 | $0.00192 |
Grade A, and why
ops-workspace 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ops-workspace
One change, one clean place to build it.
Visibility: supporting primitive. Only ops-change calls it. A framework loop must
not — the loop does not know whether this repo needs a worktree, a container, a seeded
database, or nothing at all, and the moment a loop decides that, the engine has learned a
product fact.
Invocation
ops-workspace <action> '<context-json>'
| Action | Context | Returns |
|---|---|---|
prepare |
{ branch } |
{ ok, path, reused, fidelity, notes } |
teardown |
{ path } |
{ ok } |
An absent context is {}. Reject any other action.
Repo facts both actions depend on
Worktrees live at .claude/worktrees/<slug>, which is gitignored. The slug is the branch
name with the feature/ segment dropped and remaining slashes flattened to dashes:
v18/feature/issue-159-embedded-config-references → v18-issue-159-embedded-config-references.
The base is the line's own integration branch. For a vN/feature/* branch, root it on
origin/vN/dev; fall back to origin/vN/main only if that line has no dev. Version lines
are never forward-merged — never root a v17 branch on anything from v18, and vice versa.
.githooks/pre-push rejects any branch that is not vN/dev, vN/main,
vN/{feature,release,hotfix}/* or claude/*. A workspace on a branch outside that set cannot
be pushed, so treat an off-pattern branch as an error rather than creating a tree for it.
Package feeds need no credentials. NuGet.config and .npmrc are both committed and point
at public feeds (nuget.org, MyGet umbracoprereleases, MyGet umbraconightly). A worktree gets
them from the checkout. Never add a feed, a token or a packageSourceCredentials block here.
No database to provision. The integration tests are self-contained — azure-pipelines.yml
runs dotnet test Umbraco.Automate.slnx with no SQL service and no container. A plain worktree
is therefore full CI parity, and prepare MUST NOT stand up a database, a container or a
demo site.
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 First seen · 156 lines · 88 tokens per session scan A 5ac144907f86
ops-workspace is a skill published in the GitHub repository umbraco/Umbraco.Automate (5 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,918 once invoked, about $0.0004 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…