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/shrwnsan/vibekit-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/plugins/shrwnsan/vibekit-claude-plugins/haku)<a href="https://agentmods.dev/plugins/shrwnsan/vibekit-claude-plugins/haku"><img src="https://agentmods.dev/badge/plugins/shrwnsan/vibekit-claude-plugins/haku/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/plugins/shrwnsan/vibekit-claude-plugins/haku"><img src="https://agentmods.dev/badge/plugins/shrwnsan/vibekit-claude-plugins/haku.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
haku 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 10d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What it installs
The manifest is a name and a version. 52 skills, 22 agents travel with it, and installing the plugin installs all of them — 4,850 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill doctor A 0 tokens
- Skill engineering-health A 0 tokens
- Skill manage-glue-workers A 90 tokens
- Skill patterns-watch A 86 tokens
- Skill product-pulse A 109 tokens
- Skill promo-case-glue A 83 tokens
- Skill psychological-safety A 93 tokens
- Skill pulse-synthesize A 100 tokens
- Skill stakeholder-reflect A 91 tokens
- Skill stakeholder-register A 112 tokens
- Skill strategy-doc A 0 tokens
- Skill team-close-gap A 101 tokens
- Skill team-diagnosis A 0 tokens
- Skill team-lifecycle A 0 tokens
- Skill team-style-inventory A 0 tokens
- Skill user-profile A 0 tokens
- Skill wins-curate A 99 tokens
- Skill workload-equity A 0 tokens
- Skill career-retro A 95 tokens
- Skill coaching-mode A 85 tokens
- Skill commitments A 96 tokens
- Skill decision-log A 0 tokens
- Skill exec-readout-prep A 97 tokens
- Skill feedback-frameworks A 85 tokens
- Skill glue-audit A 80 tokens
- Skill hiring-craft A 83 tokens
- Skill impact-audit A 85 tokens
- Skill influence-without-authority A 95 tokens
- Skill leadership-os A 80 tokens
- Skill metrics-design A 87 tokens
- Skill one-on-one-prep A 92 tokens
- Skill performance-management A 0 tokens
- Skill premortem A 96 tokens
- Skill prioritization-frameworks A 89 tokens
- Skill read-the-room A 83 tokens
- Skill report-career-architect A 99 tokens
- Skill report-promo-case A 99 tokens
- Skill self-reflect A 102 tokens
- Skill stakeholder-due A 94 tokens
- Skill start A 0 tokens
- Skill team-charter A 110 tokens
- Skill team-check-in A 0 tokens
- Skill team-workspace A 0 tokens
- Skill tech-strategy-writer A 101 tokens
- Skill visibility-sponsorship A 90 tokens
- Skill weekly A 0 tokens
- Skill wins-due A 70 tokens
- Skill wins-log A 0 tokens
- Skill capture A 0 tokens
- Skill stakeholder-manage B 110 tokens
- Skill demo-prep B 81 tokens
- Skill stakeholder-synthesize B 0 tokens
- Agent the-career-coach A 97 tokens
- Agent the-gtm-planner A 0 tokens
- Agent the-program-manager A 109 tokens
- Agent the-vendor-evaluator A 104 tokens
- Agent the-data-storyteller A 79 tokens
- Agent the-discovery-facilitator A 0 tokens
- Agent the-eval-designer A 73 tokens
- Agent the-explainer A 93 tokens
- Agent the-incident-responder A 117 tokens
- Agent the-postmortem-facilitator A 99 tokens
- Agent the-retro-facilitator A 98 tokens
- Agent the-rfc-reviewer A 66 tokens
- Agent the-slo-designer A 89 tokens
- Agent the-status-crafter A 99 tokens
- Agent the-prompt-critic A 59 tokens
- Agent the-research-synthesizer A 76 tokens
- Agent the-spec-writer A 79 tokens
- Agent the-translator A 95 tokens
- Agent the-architect A 60 tokens
- Agent the-red-teamer A 59 tokens
- Agent the-scientist A 51 tokens
- Agent the-reducer A 0 tokens
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.
- 10d ago Changed 4d62133a84d4
- 1mo ago First seen · 9 lines scan A 493efefa91e1
haku is a plugin published in the GitHub repository shrwnsan/vibekit-claude-plugins (7 stars, last pushed 2d ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-10.
Other plugins, from other repositories
desktop-notification
Alert you when Claude Code needs input: an audible terminal bell, an OSC 9 terminal notification, and an OS-native toast (macOS/Linux) on permission and idle prompts.
adhd
Shapes assistant output for a reader with ADHD: action-first and low-friction. adhd:shape is a standing session posture: lead with the next action, number steps, restate state across turns, cap and rank lists, give time estimates, cut preamble. adhd:clarify reshapes one dense, decision-heavy message: one decision at a.
disk-hygiene
Context-aware disk hygiene for arbitrary directory trees: inventories orphaned and temporary artifacts, classifies evidence into review tiers, and offers exact-path cleanup only after a fresh safety preview and explicit per-tier approval. The target is read-only by default; OS-managed paths, links and mount points…
naming
Generates and evaluates fresh name candidates for anything, whether an identifier, file, module, skill, repo, or domain term, by distilling a structured context brief, fanning out blind, fresh-context generators from distinct lenses (responsibility-literal, moment-of-use, domain-lore), then scoring a shortlist against.
developer-experience
Helps a team build and maintain its own developer tooling: setup records the team's tooling conventions, build-cli builds command-line tools to them, and audit-tools inventories a repository's scripts, CLIs, hooks and skills and reports what to fix.
problem-solving
Problem diagnosis and solution generation workflow. Separates problem clarification from solution generation for better outcomes.