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/soulcodex/agentic/git-worktree-workspacesnpx skills add soulcodex/agentic --skill git-worktree-workspacesgit clone --depth 1 https://github.com/soulcodex/agenticWhat 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 | $0.00058 | $0.00782 |
| Opus 5 | $0.00029 | $0.00391 |
| Sonnet 5 | $0.00012 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
git-worktree-workspaces scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Worktree Workspaces Skill
Step 1 — Discover Current Repo State
git rev-parse --show-toplevel
git branch --show-current
git worktree list --porcelain
git remote show origin | sed -n '/HEAD branch/s/.*: //p'
Capture:
- Current repository root and active branch
- Existing worktrees and paths
- Remote default branch (do not assume a fixed branch name)
Step 2 — Pick Naming and Layout
Use a predictable directory pattern outside the main working tree:
REPO_ROOT="$(git rev-parse --show-toplevel)"
REPO_NAME="$(basename "$REPO_ROOT")"
WORKTREE_ROOT="$(dirname "$REPO_ROOT")/${REPO_NAME}-worktrees"
mkdir -p "$WORKTREE_ROOT"
Recommended names:
- Branch:
feat/<topic>,fix/<topic>,docs/<topic> - Path:
$WORKTREE_ROOT/<branch-slug>
Step 3 — Create a New Worktree
For a new branch:
BASE_BRANCH="$(git remote show origin | sed -n '/HEAD branch/s/.*: //p')"
NEW_BRANCH="feat/<topic>"
TARGET_PATH="$WORKTREE_ROOT/${NEW_BRANCH//\//-}"
git fetch origin "$BASE_BRANCH"
git worktree add -b "$NEW_BRANCH" "$TARGET_PATH" "origin/$BASE_BRANCH"
For an existing branch:
EXISTING_BRANCH="<branch>"
TARGET_PATH="$WORKTREE_ROOT/${EXISTING_BRANCH//\//-}"
git fetch origin
git worktree add "$TARGET_PATH" "$EXISTING_BRANCH"
Step 4 — Work Independently Per Task
Inside each worktree:
cd "$TARGET_PATH"
git status --short
git add <files>
git commit -m "feat(<scope>): <summary>"
Rules:
- One task per worktree branch.
- Keep commits scoped to that task only.
- Run project quality gates before pushing.
Step 5 — Push and Open PRs
git push -u origin "$(git branch --show-current)"
gh pr create --base "<base-branch>" --head "$(git branch --show-current)"
Use Refs #<issue> for stacked/chained PRs that should not auto-close yet.
Use Closes #<issue> only on the final PR intended to close the issue on merge.
Step 6 — Safe Cleanup (Local Only)
After a branch is merged and no longer needed locally:
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 · 121 lines · 58 tokens per session scan A 1569acbb9cbd
git-worktree-workspaces is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 782 once invoked, about $0.0003 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
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).