Borrowing it
Nothing to install: this file belongs to Aixbox/DesktopGo. 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/Aixbox/DesktopGo/desktop/.agents/skills/task-branch-lifecycle/SKILL.mdgit clone --depth 1 https://github.com/Aixbox/DesktopGoWrote 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/aixbox/desktopgo/task-branch-lifecycle)<a href="https://agentmods.dev/skills/aixbox/desktopgo/task-branch-lifecycle"><img src="https://agentmods.dev/badge/skills/aixbox/desktopgo/task-branch-lifecycle/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/aixbox/desktopgo/task-branch-lifecycle"><img src="https://agentmods.dev/badge/skills/aixbox/desktopgo/task-branch-lifecycle.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 | $0.00059 | $0.01221 |
| Opus 5.5 | $0.00024 | $0.00488 |
| Sonnet 5.5 | $0.00012 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
task-branch-lifecycle 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Branch Lifecycle
Use this skill only when explicitly invoked as $task-branch-lifecycle (or selected from the skill picker). It manages a temporary branch in the current checkout; it does not create a Git worktree and it never pushes to a remote.
Phase Detection
Determine the phase from the current conversation and Git state:
- Start: no active task branch has been recorded for this task.
- Review waiting: implementation is complete and the user has not explicitly approved cleanup.
- Cleanup: the user explicitly says the review passed and asks to finish, clean up, return, or remove the task branch.
- If the user requests changes during review, remain on the task branch and return to implementation. Do not clean up.
Keep these values in the conversation and report them at phase boundaries:
- original branch
- temporary task branch
- whether changes are committed or uncommitted
- validation commands and results
If the conversation is resumed without this state, inspect Git and ask before deleting or switching anything. Never infer the original branch from guesswork.
Start Phase
-
Inspect the repository before changing branches:
git rev-parse --show-toplevel git branch --show-current git status --short git diff --check -
Stop and ask the user to commit or stash existing changes if the working tree is dirty, if the current HEAD is detached, or if Git reports an in-progress merge, rebase, cherry-pick, or revert. Do not auto-stash, reset, clean, or discard changes.
-
Record the current branch as
original_branch. Derive a short, lowercase, hyphenated task slug and create a local-only branch using the project-safecodex/prefix:git switch -c codex/<kind>-<slug>Use
featfor additions,fixfor bug fixes, andchangeorrefactorfor modifications. If the branch already exists locally or remotely, choose a different slug; never reset or reuse it silently. -
Implement the requested task on the temporary branch. Follow the repository's other applicable skills, especially modularity, testing, and validation guidance. Keep unrelated changes out of the branch.
What ships with it
1 file 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.
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 First seen · 98 lines · 59 tokens per session scan A adcd46b99650
task-branch-lifecycle is a skill published in the GitHub repository Aixbox/DesktopGo (63 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,221 once invoked, about $0.0002 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 2026-11-07.
task-branch-lifecycle compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| task-branch-lifecycleAixbox/DesktopGo | Skill | 63 | 2d ago | MIT | A | 59 | Codex |
| hunk-launch-videomodem-dev/hunk | Skill | 9.8k | yesterday | MIT | A | 60 | Claude Code, Codex |
| ratchet-filesdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 118 | Claude Code, Codex |
| pr-description-writermohitagw15856/pm-claude-skills | Skill | 1.5k | yesterday | MIT | A | 80 | Claude Code, Codex |
| write-git-messagesNVIDIA/TensorRT-Model-Connect | Skill | 289 | today | Apache-2.0 | A | 75 | Codex |
| review-gatemajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 95 | Claude Code, Codex |
| ring:generating-release-guidesLerianStudio/ring | Skill | 218 | 6d ago | Apache-2.0 | A | 85 | Cursor |