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 rules/fullive-ai/anima/branch-and-commit-workflowgit clone --depth 1 https://github.com/Fullive-AI/AnimaWhat 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 | $0.00624 | $0.00624 |
| Opus 5 | $0.00312 | $0.00312 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
Branch-And-Commit-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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use a branch-first, commit-early workflow suitable for a maintained open source repository.
Core rule
Before making meaningful code changes, ensure the work is on a dedicated task branch rather than on a protected or shared integration branch.
Once work starts, preserve progress through small, logical, reviewable commits instead of one large accumulated diff.
Branch behavior
At the beginning of meaningful work:
- Check the current branch.
- If already on a suitable task branch for the current task, continue there.
- If on a protected or shared branch such as
main,master,develop,dev, orrelease, create and switch to a dedicated task branch before making meaningful edits. - If on a branch unrelated to the current task, create and switch to a new task branch instead of mixing concerns.
Branch naming
Use short, descriptive, task-focused branch names.
Prefer patterns such as:
fix/dashboard-refresh-bugfix/mqtt-timeout-handlingfeat/device-status-historyrefactor/adapter-payload-parserdocs/env-setup-clarificationtest/add-timeout-regression
Branch names should be:
- lowercase
- concise
- descriptive
- scoped to one task or one closely related set of changes
Avoid vague names such as:
tempmiscworkupdatesnew-branch
Commit behavior
Commit after each completed, coherent unit of work.
A commit should represent one logical step such as:
- one bug fix
- one small feature slice
- one focused refactor
- one interface update with its direct caller adjustments
- one docs update tied to a code change
- one regression test plus the related fix
Commit quality
Each commit should be:
- small enough to review easily
- coherent in purpose
- safe to revert independently
- tied to a clear intent
- validated whenever practical
Write concise commit messages that describe the intent clearly.
Prefer:
fix dashboard polling after reconnectadd regression test for adapter timeoutrefactor mqtt payload normalizationupdate docs for broker configuration
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 · 108 lines · 624 tokens per session scan A fc8d4c65e159
Branch-And-Commit-Workflow is a cursor rule published in the GitHub repository Fullive-AI/Anima (1,049 stars, last pushed 12d ago), licensed Apache-2.0. It adds 624 tokens to every session, about $0.0031 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 2026-08-30.
Other cursor rules, from other repositories
git
Conventional commit message format for git commits.
commit-checks
Run gofmt, go vet, and unit tests before committing Go files.
no-ai-attribution
Never attribute commits, comments, or contributions to AI agents.
git-commit-attribution
Git commits must use the human developer identity only; never Cursor Agent co-authorship.
git-conventional-commits
Conventional commit messages and logical multi-commit workflow when working with Git.
dos-verify-done-claims-cursorrules-prompt-file
Gate AI done/shipped/fixed claims on ground truth from the DOS kernel (dos verify, dos commit-audit) — git ancestry and the commit's own diff, never the agent's own narration.