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 closedloop-ai/claude-plugins --skill vibe-seed-refreshgit 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/skills/closedloop-ai/claude-plugins/vibe-seed-refresh)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/vibe-seed-refresh"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/vibe-seed-refresh/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/closedloop-ai/claude-plugins/vibe-seed-refresh"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/vibe-seed-refresh.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 | $0.00166 | $0.01893 |
| Opus 5.5 | $0.00066 | $0.00757 |
| Sonnet 5.5 | $0.00033 | $0.00379 |
| Haiku 4.5 | $0.00017 | $0.00189 |
Grade A, and why
vibe-seed-refresh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe seed refresh
The vibe seed fills a throwaway database and Desktop profile from code in
symphony-alpha: locally for just vibe-up, and in each seeded vibe session's
Vercel environment. Every Prisma model has a coverage file saying whether the
seed fills it (seeded), deliberately leaves it empty (skipped, with a
reason), or still owes it data (todo). Engineers add todo when they add a
model; this skill pays that debt and repairs anything else that drifted.
Run in Codex Desktop ($vibe-seed-refresh). It relies on the
gh-monitor-pr skill, which wakes this thread when the PR needs attention, so
each wake-up resumes from the state file instead of polling.
Your role: orchestrate, never do the work
This thread can live for days across monitor wake-ups, so its context is for
state and decisions only. Under all circumstances you never read source,
search the codebase, edit files, read logs or diffs, or run seeds, builds,
tests, git, or gh yourself. You read and write the state file, call the
ClosedLoop MCP for the ticket and loop, start and stop gh-monitor-pr,
commit, and dispatch workers with short briefs. Committing is yours alone,
because a commit runs the repository's commit hooks: use
node ../vibe/scripts/commit-worktree.mjs --worktree "<fix worktree>" --subject "<subject>" [--body "<text>"],
which prints short JSON. No worker commits. A commit the hook refused
("ok":false) goes to vibe-seed-fix-worker in follow-up mode with the
error, then you commit again. Workers return a short status (DONE,
BLOCKED, or DRIFT / CLEAN from the check worker).
Workers are this plugin's agents (../../agents/<name>.md; in Codex spawn a
subagent with the file's body as its instructions, in Claude Code use
vibe:<name>). Every worker uses closedloop-graph first, per
../vibe/references/closedloop-graph.md; say so in each brief.
| Worker | Job |
|---|---|
vibe-seed-check-worker |
refresh the check worktree to fresh main and report drift |
vibe-seed-fix-worker |
fix the seed in the fix worktree until the checks pass; also fixes CI failures and review comments later |
vibe-seed-pr-worker |
push and open the PR from the template; later push fixes and reply on review threads, stage a merge of main, re-enqueue, report PR state |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +16 lines d3d517b743f4
- 2d ago Changed · +1 lines · +11 tokens per session a62532038ec2
- 3d ago Changed · +4 lines 6f868d3165f8
- 4d ago First seen · 110 lines · 155 tokens per session scan A 482e1f22fab7
vibe-seed-refresh is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 166 tokens to every session and 1,893 once invoked, about $0.0007 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 skills, from other repositories
release-notes
Write release notes for a tagged release — a business-impact summary of what changed for the user, plus a thanks section naming every contributor whose commits are in the release. Short by construction.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
autoship
Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release this package", "autoship", "merge Version Packages", or diagnose a release that did not publish.
scaffold-cli
Scaffolds a TypeScript CLI and npm package with the house toolchain, dual tsdown outputs, CLI contracts, changesets, and publishing templates. Use when asked to "scaffold a CLI" or "start an npm package".
ci-speedup
Cuts the wait from push to green by measuring a pipeline's critical path from run timestamps, then splitting, sharding, trimming setup and sharing test module state, with a before/after ledger. Use when asked to "speed up CI", "CI is slow", "why does a PR take 15 minutes", "CI is the bottleneck", or when agents merge…
claw-mux
Control cmux terminal topology and I/O — send commands to panes, read output, split layouts, monitor logs, orchestrate multi-pane workflows. Requires cmux environment.