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 agentmods add skills/fusebase-dev/fusebase-flow/git-workflownpx skills add fusebase-dev/fusebase-flow --skill git-workflowgit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowWhat 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 | $0.00040 | $0.00687 |
| Opus 5 | $0.00020 | $0.00344 |
| Sonnet 5 | $0.00008 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
git-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 2d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Workflow
Purpose
Use this skill for day-to-day Git work in generated apps:
- keep commits focused and understandable,
- avoid committing secrets,
- keep rollback simple.
Baseline Workflow
- Check current state:
git status --shortgit rev-parse --abbrev-ref HEAD
- Group related changes.
- Commit with reason-focused message.
- Keep unrelated changes in separate commits.
Commit Rules
- Prefer small, scoped commits.
- Message should explain why.
- Do not commit
.env, credentials, or token files. - Avoid history rewrite unless explicitly requested.
Suggested message patterns:
feat: <why>fix: <why>chore: <why>
Rollback Guidance
Preferred shared-history rollback:
git revert <commit_sha>
Temporary local rollback during active iteration:
git reset --hard <commit_sha_before_change>
Use revert by default on shared branches.
Operations That Commonly Need Separate Commits
fusebase app create/update(fusebase.jsonchanges)fusebase update --skip-mcp --skip-deps --skip-cli-update --skip-commit(AGENTS.md,.claude/*changes)fusebase config ide/fusebase integrations(IDE MCP config changes)fusebase env create(.envlocal changes; usually not committed)
Always review git status --short after these operations.
<% if (it.flags?.includes("git-debug-commits")) { %>
Strict Debug/Deploy Traceability (Flag: git-debug-commits)
When git-debug-commits is enabled, apply these stricter rules.
These are mandatory rules (not recommendations).
Deploy Preflight (Required)
Before fusebase deploy:
git status --shortgit rev-parse --abbrev-ref HEADgit rev-parse HEAD
If tree is dirty, block deploy by default and continue only with explicit user approval.
Commit Per Verified Fix (Required)
For each verified debug fix:
git add -Agit commit -m "fix(debug): <why>"- record
git rev-parse --short HEAD
Do not batch unrelated fixes. Do not continue to the next fix until the current verified fix is committed. If a fix was verified but not committed, deploy is blocked until the commit exists.
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.
- 2d ago First seen · 112 lines · 40 tokens per session scan A e624771804d7
git-workflow is a skill published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 687 once invoked, about $0.0002 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
adobe-express-core
Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.
adobe-express-monetization
Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.
adobe-express-spectrum-ui-ux
Build or review Adobe Express add-on panel UI with Spectrum patterns, stack selection guidance (raw SWC, swc-react, React Spectrum), Express theme setup, state and navigation design, and actionable UX quality checks. Use when implementing or auditing panel layouts, interaction states, multi-screen flows, and…
adobe-express-cors-and-backend
Diagnose and fix CORS errors between Adobe Express add-on UI and backend APIs across local development, private listing, and public listing stages. Use when browser requests fail with preflight, Access-Control-Allow-Origin, Access-Control-Allow-Headers, or OPTIONS issues; when moving from localhost to hosted add-on…
adobe-express-document-manipulation
Create and modify document content in Adobe Express add-ons using Document SDK. Use when planning document operations, inserting shapes/text/media, sequencing sandbox commands, or troubleshooting document edits.
adobe-express-oauth-authentication
Implement OAuth 2.0 and authentication flows for Adobe Express add-ons. Use when connecting to cloud providers (Dropbox, OneDrive, Google Drive), managing tokens, storing credentials, or designing login surfaces.