Borrowing it
Nothing to install: this file belongs to saagpatel/mcpforge. 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/saagpatel/mcpforge/main/.agents/skills/mcpforge-cloud-workflow/SKILL.mdgit clone --depth 1 https://github.com/saagpatel/mcpforgeWrote 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/saagpatel/mcpforge/mcpforge-cloud-workflow)<a href="https://agentmods.dev/skills/saagpatel/mcpforge/mcpforge-cloud-workflow"><img src="https://agentmods.dev/badge/skills/saagpatel/mcpforge/mcpforge-cloud-workflow/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/saagpatel/mcpforge/mcpforge-cloud-workflow"><img src="https://agentmods.dev/badge/skills/saagpatel/mcpforge/mcpforge-cloud-workflow.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 | $0.00033 | $0.01127 |
| Opus 5.5 | $0.00013 | $0.00451 |
| Sonnet 5.5 | $0.00007 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
mcpforge-cloud-workflow 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Forge Cloud workflow
Use for authorized Cloud work or a requested PR follow-up in MCP Forge. Detect
the Git root with git rev-parse --show-toplevel; run commands from that root.
Read the nearest applicable AGENTS.md, supplied working
instructions, and any referenced prepared-environment startup guide first.
Startup and scope
- Inspect the repository identity, local branch, HEAD, and
git status --short. Preserve unrelated changes, existing branches, and tracked manifests/locks. Use the existing isolated Cloud checkout; no extra worktree is needed by default. - Prepared startup permits authorized source edits and commits. Follow its cache
variables and pinned Python argument for
uv sync --check --locked --offline. Skip refresh if it passes. Only a stale local editable package permits the correspondinguv sync --locked --offlinerefresh, followed by a recheck. Investigate other mismatches; do not invent a fresh install, upgrade dependencies, or change locks to hide a startup problem. - Local tools, configuration, sign-ins, and credentials do not automatically
transfer. Do not read credentials,
.envfiles, keychains, OAuth stores, browser profiles, or raw private logs. Preserve network, privacy, approval, and secret settings. - Follow the current user's model preferences: GPT-6.1 Sol High for normal coding, coordination, and review; Medium for routine or clearly bounded work and helpers. Do not automatically escalate to Max, Extra High, or Ultra. Preferences do not configure the parent model picker, and helpers require supported native capabilities.
Continue the requested PR
Resolve the exact repository and PR through supported GitHub tools. Read its current open/closed/merged status, head repository/branch/commit, and base. Compare those with local HEAD/status before editing. Continue that branch only when open and consistent with the current authorization; do not create a duplicate PR or blindly continue a closed/merged PR. Follow-up scope does not imply merge authority.
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.
- 1mo ago First seen · 98 lines · 33 tokens per session scan A 24220baa0a91
mcpforge-cloud-workflow is a skill published in the GitHub repository saagpatel/mcpforge (0 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 1,127 once invoked, about $0.0001 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 2026-10-05.
mcpforge-cloud-workflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcpforge-cloud-workflowsaagpatel/mcpforge | Skill | 0 | 3d ago | MIT | A | 33 | Claude Code, Codex |
| git-flowWrongStack/WrongStack | Skill | 404 | yesterday | MIT | A | 110 | Claude Code, Codex |
| git-flow-prsoulcodex/agentic | Skill | 10 | 7d ago | MIT | A | 103 | Claude Code, Codex |
| commitnikolay-e/diffctx | Skill | 6 | yesterday | Apache-2.0 | A | 41 | Claude Code |
| git-workflowprofclaw/profclaw | Skill | 16 | 1mo ago | AGPL-3.0 | A | 19 | Claude Code, Codex |
| git-advanced-workflowsHermeticOrmus/claude-code-game-development | Skill | 78 | 1mo ago | MIT | A | 54 | Claude Code |
| diff-reviewwolfenazz/YzPzCode | Skill | 20 | yesterday | Apache-2.0 | A | 39 | Claude Code, Codex |