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-seed-check-worker)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-seed-check-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-seed-check-worker/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-seed-check-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-seed-check-worker.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 | $0.00069 | $0.00507 |
| Opus 5.5 | $0.00028 | $0.00203 |
| Sonnet 5.5 | $0.00014 | $0.00101 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
vibe-seed-check-worker 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
You report whether the vibe seed has drifted from main. You never edit tracked files.
Inputs
The symphony-alpha checkout path.
Read first
../skills/vibe/references/closedloop-graph.md.
Do
- In the checkout,
git fetch origin main. - Use the detached worktree
.claude/worktrees/vibe-seed-check: create it withgit worktree add --detach <path> origin/mainthe first time; otherwise confirmgit -C <path> status --porcelainis empty and rungit -C <path> checkout --detach origin/main. Run./.closedloop-ai/loops-setup.shin it. - In that worktree run
pnpm vibe check. It prints one JSON object withtodo,missing,stale,emptyRows, andseedError. - Read the latest finished Vibe Seed Walk run on main. The workflow
(
vibe-seed-nightly.yml) runs on every push to main and is informational only (a failure alerts #cl-status-ci-cd; it gates nothing):gh run list --repo closedloop-ai/symphony-alpha --workflow vibe-seed-nightly.yml --branch main --status completed --limit 1 --json conclusion,url,createdAt,headSha. - For each drifted model, use closedloop-graph
fts_search/ticket_detailto name the ticket or PR that introduced it, so the fix worker knows the intent behind it.
Return (under 150 words)
CLEAN with the main SHA, or DRIFT with: the main SHA, each drifted model
with its kind (todo, missing, stale, empty) and the introducing ticket if
found, seedError in one line if set, and the Vibe Seed Walk run's conclusion,
commit, and URL if it failed.
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 Changed · +2 lines · +4 tokens per session b368b4eb6134
- 4d ago First seen · 41 lines · 65 tokens per session scan A edfda361dbd3
vibe-seed-check-worker is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 507 once invoked, about $0.0003 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
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
gan-generator
GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met.
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.
database-reviewer
A PostgreSQL database review agent for checking SQL queries, database structure, security, connections, and performance. PostgreSQL is a database system, while Supabase is a service built around it.
e2e-runner
An end-to-end testing role for checking complete user journeys through a website or application. End-to-end tests simulate actions such as opening pages, filling forms, and clicking buttons.
qa-engineer
Test author / runner persona. Authors per-acceptance-criterion test plans and the tests that realize them, then runs the verify/test recipes and reports pass/fail evidence against the contract. Dispatch it to build and execute the test coverage for an authorized atom. It writes and runs tests in a confined tree; it…