Borrowing it
Nothing to install: this file belongs to bestagentkits/cloud-harness-mcp. 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/bestagentkits/cloud-harness-mcp/main/.agents/skills/cloudharness/SKILL.mdgit clone --depth 1 https://github.com/bestagentkits/cloud-harness-mcpWrote 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/bestagentkits/cloud-harness-mcp/cloudharness)<a href="https://agentmods.dev/skills/bestagentkits/cloud-harness-mcp/cloudharness"><img src="https://agentmods.dev/badge/skills/bestagentkits/cloud-harness-mcp/cloudharness/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/bestagentkits/cloud-harness-mcp/cloudharness"><img src="https://agentmods.dev/badge/skills/bestagentkits/cloud-harness-mcp/cloudharness.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 | $0.00097 | $0.04153 |
| Opus 5.5 | $0.00039 | $0.01661 |
| Sonnet 5.5 | $0.00019 | $0.00831 |
| Haiku 4.5 | $0.00010 | $0.00415 |
Grade A, and why
cloudharness 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 today.
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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Harness MCP
Use Cloud Harness as a private, single-owner remote coding harness. It clones an approved repository into a TTL-limited executor and exposes bounded MCP tools. This skill guides effective and safe tool use; it does not grant credentials, host access, Docker authority, deployment authority, or permission to weaken network isolation.
Read the relevant reference
| Need | Read |
|---|---|
| Install the skill, connect a client, use the MCP gateway surface, or understand trust boundaries | Installation and security |
| Choose a tool and locate its detailed contract | Tool reference index |
| Open, recover, inspect, or close a workspace; interpret results/errors | Workspace lifecycle and results |
| List, read, write, patch, move, delete, grep, or search symbols | Files and search |
| Run a command, interactive shell, coding session, or dependency task | Execution and tasks |
| Install, update, roll back, or uninstall a durable CLI tool for every workspace | Managed packages |
| Inspect or change Git state, transfer origin refs, or use worktrees | Git and worktrees |
| Run an automated merge train: branch locks, commit statuses, check runs, review state, workflow dispatch and re-runs | GitHub merge train |
| Create a new organization repository and bootstrap it (only when the user explicitly asks) | GitHub repository bootstrap |
| Read/run repository skills, hooks, knowledge (memories & journals), or deployments | Repository automation |
| Snapshot, list, read, restore, or delete retained artifacts | Retained artifacts |
| Choose a subagent model, check a connection, save an agent model profile, or read estimated model spend | Models and spend |
What ships with it
13 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.
- evals/evals.json 4.0 KB
- references/artifacts.md 3.4 KB
- references/execution-and-tasks.md 14 KB
- references/files-and-search.md 6.3 KB
- references/git-and-worktrees.md 18 KB
- references/github-merge-train.md 6.5 KB
- references/github-repository-bootstrap.md 6.0 KB
- references/installation-and-security.md 9.1 KB
- references/managed-packages.md 5.4 KB
- references/models-and-spend.md 9.3 KB
- references/repository-automation.md 12 KB
- references/tool-reference.md 4.3 KB
- references/workspace-lifecycle-and-results.md 16 KB
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.
- today Changed · +10 lines 4d394c41bf9b
- 9d ago Changed · +34 lines · +11 tokens per session b68141dffa01
- 12d ago Changed · +5 lines 5b68569f0ac3
- 13d ago Changed · +18 lines 5d81536579ed
- 14d ago Changed · +15 lines 82ee5d03eea2
- 1mo ago Changed · +5 lines c76d4af8171d
- 1mo ago Changed · +5 lines 6db56763ea3b
- 1mo ago Changed · +7 lines 5f3bcc8a8273
- 1mo ago Changed · +28 lines b12961d95d00
- 1mo ago First seen · 141 lines · 86 tokens per session scan A 0bb1ceb041eb
cloudharness is a skill published in the GitHub repository bestagentkits/cloud-harness-mcp (94 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 4,153 once invoked, about $0.0004 per session on Opus 5.5. 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
task-final-report
Apply the final report and PR publication procedure for a Hyper-Waterfall task. Write the final report (report.md), mark the daily task board complete, create the final commit, push the remote publish/task{N} branch, and create an Open PR to {BASEBRANCH}. Invoke only immediately before PR publication after all stages…
pr-merge-cleanup
Apply cleanup after confirming a PR merge. Close the GitHub Issue, delete the remote publish/task{N} branch, clean up the local local/task{N} branch and separate worktree, and return to {BASEBRANCH}. Invoke only after the PR is actually merged.
task-stage-report
Apply the stage completion procedure for a Hyper-Waterfall task. Write the stage report (stage{N}.md), commit stage source and report together, and run stage verification commands. Invoke after a stage completes and before entering the next stage.
task-start
Apply the Hyper-Waterfall task start procedure. Confirm the GitHub Issue, update {BASEBRANCH}, create local/task{N}, add a daily task board row, and create the task plan template. Use before starting new code or documentation changes.
release
Release a new version of the mumei repository. Invoke when the user gives an explicit release instruction ("release it", "/release", "patch release", "ship 0.2.0"). Takes no argument or "patch" / "minor" / "major" for a SemVer bump, or a direct version such as "0.2.0". Wraps any uncommitted changes into a single…
storozh
Advisory semantic guard over a changeset manifest before it lands in shared state. Use after a multi-repo session produces a changeset-manifest (mirabilis C1) and before the co-sign push gate — classify each unit's routing against the darwin routing-policy (C3) and NLI-check each unit against the shield corpus (claims…