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/harshanandak/forge/worktree-flownpx skills add harshanandak/forge --skill worktree-flowgit clone --depth 1 https://github.com/harshanandak/forgeWhat 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 | $0.00055 | $0.00528 |
| Opus 5 | $0.00028 | $0.00264 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
worktree-flow 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.
What it actually says
worktree-flow
Two agents in one checkout collide on HEAD mid-task. The isolation is not optional and the primary checkout is not yours. [Forge #6 ×4]
Create
forge worktree create <slug>
Run it from the primary repo root — create and clean are cwd-scoped.
forge worktree create does three things raw git worktree add does not: it
links the kernel issue, sets up the issue store, and wires dependencies.
[Forge #6 ×4]
Then work entirely inside .worktrees/<slug>/.
Two things that bite on Windows
node_modulesis a root-only junction. A fresh worktree is missingpackages/skills/node_modules; junction it or the skills tests fail on a missingchalk/inquirer.- Long paths. After
git worktree remove --force, a leftover directory may need a\\?\-prefixed delete.
Clean
forge clean
Fast-forward local main/master first, or squash-merge detection misses your
branch and the worktree is left behind. forge clean has no default-branch
guard — run it from the primary root and know which branch you are on.
Working alongside other agents
- One agent, one worktree, one PR. Two agents leading the same PR is a correction Harsha has made repeatedly. [Forge #6 ×4]
- Parallel agents state file ownership up front, before either starts editing.
- Never call another agent dead from one sample. A clean tree and no recent writes also describes an agent between a commit and its next red test. Sample twice, minutes apart, and compare. Any respawn must refuse to edit a contended worktree.
- If you are asked to work in the primary checkout while another stream is live, say no and create a worktree.
Done when
Your changes live on a branch inside .worktrees/<slug>/, the primary checkout
is untouched, and the worktree either has an open PR or has been cleaned.
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 · 62 lines · 55 tokens per session scan A 98dc0ac68b4a
worktree-flow is a skill published in the GitHub repository harshanandak/forge (4 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 528 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…