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/miaodx/intuitive-flow/intuitive-port-worktreenpx skills add MiaoDX/intuitive-flow --skill intuitive-port-worktreegit clone --depth 1 https://github.com/MiaoDX/intuitive-flowWrote 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/miaodx/intuitive-flow/intuitive-port-worktree)<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/intuitive-port-worktree"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/intuitive-port-worktree.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.02190 |
| Opus 5 | $0.00039 | $0.01095 |
| Sonnet 5 | $0.00016 | $0.00438 |
| Haiku 4.5 | $0.00008 | $0.00219 |
Grade A, and why
intuitive-port-worktree 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 6d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intuitive Port Worktree
Use this skill to move a change set from a source worktree into the target default repo checkout while preserving the target checkout's current branch.
The operation name depends on the method:
- cherry-pick: replay one or more source commits directly.
- apply a patch: apply a diff generated from the source.
- manual patch port or manual cherry-pick: map the same intent into a target branch whose files or APIs have diverged.
- port changes or transplant changes: generic phrasing for this workflow.
Operating Rule
Do not switch the target repo to the source branch unless the user explicitly asks. The target repo's current branch is the destination.
If source and target paths are explicit, execute autonomously. Ask only when the source payload or target repo is ambiguous enough that the wrong choice would overwrite unrelated work.
Discovery
Collect this before editing:
- status, root path, branch, recent commits, and target worktree list;
- whether source and target share
rev-parse --path-format=absolute --git-common-dir.
If they do not share a git common dir, the workflow can still use patches, but commit refs from the source may not resolve in the target.
Payload Selection
Prefer the smallest faithful payload:
- If the user names commit hashes, use those commits.
- If the source branch has local commits not in target, inspect the range from
the merge base to source
HEAD. - If the source worktree is dirty, include staged and unstaged diffs only after
confirming they are intentional from
git statusandgit diff --stat. - If both commits and dirty changes exist, port commits first, then dirty diffs.
Inspect commit ranges and dirty diffs with git log --oneline --reverse and
git diff --stat before selecting the payload.
Safety Gate
Before modifying the target:
- Read the target status. Do not overwrite unrelated target changes.
- If target is dirty, check whether changed paths overlap the port. If they do, stop and ask; otherwise keep the edits separate.
- Create a lightweight
backup-before-port-<timestamp>branch in the target.
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.
- 6d ago First seen · 237 lines · 79 tokens per session scan A 5cbd7e7c1107
intuitive-port-worktree is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 2,190 once invoked, about $0.0004 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 skills, from other repositories
release
Create a new release with version bump, release notes, commit, and tag.
sub-audit
Run a code review and documentation audit on recent changes. Finds bugs, edge cases, missing docs, and type safety issues.
sub-docs
Sync all SubFrame documentation after feature work. Updates AGENTS.md lists, changelog, PROJECTNOTES decisions, and STRUCTURE.json.
sub-ipc
Regenerate the IPC channel reference documentation from ipcChannels.ts type maps.
sub-tasks
View and manage SubFrame Sub-Tasks. Use when starting work, completing tasks, checking what's pending, or creating new tasks from conversation.
onboard
Analyze project intelligence files and bootstrap SubFrame's STRUCTURE.json, PROJECTNOTES.md, and initial sub-tasks from existing codebase context.