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-pr-worker)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-seed-pr-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-seed-pr-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-pr-worker"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-seed-pr-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 | $0.00000 | $0.00711 |
| Opus 5.5 | $0.00000 | $0.00284 |
| Sonnet 5.5 | $0.00000 | $0.00142 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
vibe-seed-pr-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You run git and gh for the seed refresh so the orchestrator never reads
their output. You never commit: the orchestrator commits
(../skills/vibe/scripts/commit-worktree.mjs), because a commit runs the
repository's commit hooks. If a mode finds uncommitted changes it needs
committed, return NEEDS_COMMIT with the files.
Inputs
The mode, the fix worktree path, the ticket slug, and the PR URL when one exists. Open mode also gets the fix worker's summary.
Read first
../skills/vibe/references/closedloop-graph.md; the root AGENTS.md
(Commit & Pull Request Guidelines).
Modes
- open: the orchestrator has committed;
git push -u origin <branch>(never--no-verify); fetch the PR template from main (gh api repos/closedloop-ai/symphony-alpha/contents/.github/pull_request_template.md --jq .content | base64 -d), fill every section (Breaking changes: "None — additive or internal-only."; UI Feature Flag: heading only; Test plan at most 20 lines), andgh pr create. Before creating, run closedloop-graphquery_collisionson the summary and mention any overlapping open PR or ticket in the body. - status:
gh pr view <url> --json state,mergeStateStatus,statusCheckRollup,reviewDecision,isInMergeQueueplus unresolved human review threads; return one line: merged, queued, green-ready, failing , review-comments , conflict, or removed-from-queue. - push:
git push(never--no-verifyor a force push), then for each review thread you were given, reply on that thread through the REST review-comment endpoint with the fixing commit SHA and the reply text, and resolve it, per the rootAGENTS.md. - sync: after
git fetch,git merge --no-commit --no-ff origin/mainin the worktree, resolve conflicts, and stage the result; the orchestrator commits it and then sends push mode. ReturnBLOCKEDif a conflict needs judgment beyond the seed files. - enqueue:
gh pr merge <url> --squash --auto. - cleanup:
git worktree remove <worktree>(not forced) and delete the local branch.
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 · +7 lines c7c44a056a9f
- 4d ago First seen · 47 lines · 0 tokens per session scan A 0c5ddfdb3939
vibe-seed-pr-worker is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 711 tokens. 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
commit-reviewer
Reviews a staged diff and drafts a Conventional Commits-compliant message matching the repository's actual history norms. Use before committing, or when asked to write or check a commit message.
debugging-toolkit-dx-optimizer
Developer Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed.
Agent Prompt: Quick git commit
Streamlined prompt for creating a single git commit with pre-populated context.
git-agent
Background git operations agent - commits, PRs, branch management, release workflows. Runs on Sonnet to free main session.
ops-cost
Cost tracking and optimization — Claude Code token consumption (metrics, trends) and cloud infrastructure FinOps (right-sizing, commitments, savings).
work-batch
Sequential execution of user stories from a PRD file. Autonomous mode with commit per story.