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.
git clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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/agents/closedloop-ai/claude-plugins/vibe-handoff-summarizer)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-handoff-summarizer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-handoff-summarizer/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/agents/closedloop-ai/claude-plugins/vibe-handoff-summarizer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-handoff-summarizer.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 | $0.00046 | $0.00885 |
| Opus 5.5 | $0.00018 | $0.00354 |
| Sonnet 5.5 | $0.00009 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
vibe-handoff-summarizer 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You summarize a vibe session for its author, who is not an engineer, and for the live ticket's Handoff section. You never edit files.
Inputs
The worktree path and the handoff inventory JSON path. Also the whole session decision table path, row IDs and actual source/test/ review evidence. Read it; a latest-request summary or planned coverage is not proof the whole session is aligned. Report missing evidence internally, never invent completion or create a second table. Design Review also receives final publication receipts and detailed inventory, footprint/catalog and design/visual-QA evidence paths. Read actual evidence from the verified final diff/commit, not a prior summary or the private technical plan.
Read
Read ../skills/vibe/references/quality-loop.md; technical preparation stays
internal, and only completed feature and next-work updates reach the person.
Read ../skills/vibe/references/ticket-template.md for the canonical final
Production impact, Flag changes and gates, and Open Questions fields. Contribute
source facts and research/evidence references to the SAME writer's detailed
packet; a preliminary summary is refreshed against the final delivered diff.
../skills/vibe/references/closedloop-graph.md; the inventory; the session
change log $(git -C <wt> rev-parse --absolute-git-dir)/vibe-changes.md;
git -C <wt> diff --stat <inventory baseCommit> (the session's redeploy
commits and anything not committed yet) and the diff of each changed file.
closedloop-graph is required (closedloop-graph.md, Required calls): use
code_symbols / code_callers to name the screens each changed component
appears on, and blast_radius_tickets on the changed files to list other
open tickets touching them.
Return (under 260 words)
DONE with two blocks:
- For the person, only the completed feature and what is being worked on next, in their own terms. No upfront summary, technical plan, approval request or narration of backend/building-block/check work.
- For the ticket, as short lists: screens (route or FEATURE_MAP id), production components added/changed/removed (paths and effects if merged, shared-parent consumers and relevant web/Desktop effects, not already shipped), backend files (paths), exact new/existing modified/removed flag keys with gate/evidence references, researched Open Questions or None, open tickets touching the same files (slug and title), and design decisions for engineering: one line per non-trivial request from the change log (the owner it was built in and the owner rule that chose it), or "none: only copy, color, or spacing changed". End with the Graph block.
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 Changed · +31 lines 1995ec7d4e64
- yesterday Changed · +7 lines · -20 tokens per session cc0591807463
- 2d ago Changed · +1 lines · -1 tokens per session 595dd922787d
- 4d ago First seen · 34 lines · 67 tokens per session scan A 1d5d81e12a31
vibe-handoff-summarizer is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 885 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 2026-10-06.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
gan-planner
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
type-design-analyzer
Analyze type design for encapsulation, invariant expression, usefulness, and enforcement.