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 skills add dannote/dot-pi --skill vibe-mergegit clone --depth 1 https://github.com/dannote/dot-piWrote 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/dannote/dot-pi/vibe-merge)<a href="https://agentmods.dev/skills/dannote/dot-pi/vibe-merge"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/vibe-merge/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/dannote/dot-pi/vibe-merge"><img src="https://agentmods.dev/badge/skills/dannote/dot-pi/vibe-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.00689 |
| Opus 5 | $0.00026 | $0.00345 |
| Sonnet 5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
vibe-merge 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Merge
Vibe-merge means: mine a PR/branch for good ideas, implement the worthwhile parts ourselves in small reviewable commits, and credit the original contributor with Co-authored-by trailers. Do not merge the branch wholesale unless the user explicitly asks.
Workflow
-
Inspect the source
- Read the PR/branch metadata, diff, commits, discussion, requested changes, external reviews, and checks.
- Identify the original author name/email from commits when possible:
git show -s --format='%an <%ae>' <commit>- If the email is private/unusable, use the GitHub noreply identity from the PR author when available.
- Write down the useful ideas and the risky parts separately.
-
Pick one idea at a time
- Start from the target base branch, not from the PR branch.
- Implement the idea in the project's style and architecture.
- Prefer smaller commits over a broad mixed rewrite.
- Do not copy large code blocks blindly; adapt or reimplement to fit current abstractions.
- Keep unrelated PR churn out of the commit.
-
Validate each idea
- Run focused tests for the touched area.
- Run the repo's normal check command before finalizing if feasible.
- If the PR idea has known review findings, fix them during the reimplementation instead of importing the bug.
-
Credit the contributor
-
Every commit that incorporates a contributor's idea must include a trailer:
Co-authored-by: Contributor Name <[email protected]> -
If multiple contributors materially influenced the idea, include multiple trailers.
-
Do not claim sole authorship for ideas mined from external PRs.
-
-
Communicate clearly
- Say which PR/branch the idea came from.
- Mention that it was reimplemented rather than merged directly.
- Draft any reply after reading the full conversation; do not repeat context the contributor already knows or expose private reasoning.
- Show the exact reply and wait for approval before posting.
- When closing or commenting on the original PR, thank the contributor and explain briefly that selected ideas landed with co-author credit.
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 Changed · +2 lines b8ee2ca7853a
- 10d ago First seen · 66 lines · 53 tokens per session scan A 7c43496d42ab
vibe-merge is a skill published in the GitHub repository dannote/dot-pi (51 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 689 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 2026-08-30.
Other skills, from other repositories
speq-plan-pr
Headless, non-interactive version of /speq-plan for CI or agent-driven runs. Plans a feature without a live interview, commits the result to a feat/plan-name branch, and opens a draft PR. If a decision genuinely needs a human, it persists the partial plan and open questions and asks in a PR comment instead of…
speq-implement-pr
Headless follow-up to /speq-plan-pr. Continues a plan on its feat/plan-name branch and runs it end-to-end: implements via /speq-implement, bumps the version, commits and pushes, runs the real test suites, records only if green, then opens/updates the PR and marks it ready. Resumes from the PR Lifecycle checkpoint in…
speq-git-operations
The git/gh operation-to-command mapping, safety rules, and return formats — invoked directly by the headless orchestrators speq-plan-pr and speq-implement-pr, the only components permitted to write git history or touch a remote.
speq-git-discipline
Read-only git guardrails and the Conventional Commits reference — no history writes, verify changes before completing. Triggered by planner-agent, implementer-agent, implementer-expert-agent, and recorder-agent. The headless orchestrators speq-plan-pr and speq-implement-pr are the sole exception: they write git…
mine-plan-exec
Execute one repository implementation plan end to end in its MINE-prepared linked worktree. Use when the user invokes mine-plan-exec with a plan ID or file, asks to implement a governed plan, or wants dependency checks, code changes, verification, reporting, commits, and graph updates. Never implement directly on…
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.