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 kks0488/vibe-codex --skill vc-agent-teamsgit clone --depth 1 https://github.com/kks0488/vibe-codexWrote 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/kks0488/vibe-codex/vc-agent-teams)<a href="https://agentmods.dev/skills/kks0488/vibe-codex/vc-agent-teams"><img src="https://agentmods.dev/badge/skills/kks0488/vibe-codex/vc-agent-teams/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/kks0488/vibe-codex/vc-agent-teams"><img src="https://agentmods.dev/badge/skills/kks0488/vibe-codex/vc-agent-teams.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 | $0.00045 | $0.00467 |
| Opus 5.5 | $0.00018 | $0.00187 |
| Sonnet 5.5 | $0.00009 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
vc-agent-teams 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 2mo 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
VC Agent Teams
Purpose
Use vc teams when coordination state must survive a process or session boundary, or when an
inspectable local mailbox is itself a requirement.
For ordinary parallel exploration, testing, triage, or review inside one Codex session, use Codex's
built-in subagents. vc teams stores and validates messages; it does not spawn agents.
Workflow
- Decide whether persistence is truly required. If not, use built-in subagents.
- Create a narrowly named team.
- Add only the roles needed by the workflow.
- Send bounded tasks with expected outputs and scope.
- Match approval or shutdown responses by
requestId. - Read status and evidence before closing the team.
- Prune stale read messages and delete finished teams.
Commands
vc teams create --name release-audit --description "durable release coordination"
vc teams add-member --team release-audit --name reviewer --agent-type reviewer
vc teams send --team release-audit --type message --from team-lead --recipient reviewer --content "Review release evidence"
vc teams status --team release-audit
vc teams read --team release-audit --agent reviewer --unread
vc teams await --team release-audit --agent team-lead --request-id <id> --timeout-ms 15000 --json
vc teams prune --team release-audit --days 7
vc teams delete --name release-audit --force true
State is stored under ~/.vc/teams/{team-name} unless VC_TEAMS_DIR overrides the location.
Safety rules
- Treat mailbox content as local data that may contain project context; do not commit it.
- Prefer direct messages to broadcasts.
- Do not represent a queued mailbox message as completed agent work.
- Require a matching pending request for approval and shutdown responses.
- Use a timeout for waits and report timeouts honestly.
What ships with it
2 files 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.
- 2mo ago First seen · 50 lines · 45 tokens per session scan A 7c41fcacf76a
vc-agent-teams is a skill published in the GitHub repository kks0488/vibe-codex (11 stars, last pushed 20d ago), licensed MIT. It adds 45 tokens to every session and 467 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 2026-08-30.
Other skills, from other repositories
loop
Use only when user explicitly invokes $loop.
generating-python-installer
Commercial-grade Python installer expert for Windows: Nuitka extreme compilation, dist slimming, DLL footprint analysis, and Inno Setup packaging to ship the smallest, fastest installers. Use when a Python app must ship as a minimal, fast-starting Windows installer; not for basic script-to-exe conversion. Relevant…
boss-advanced
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
gstack-sprint
3-Phase Sprint workflow — design → execute → review with user interaction at decision points.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
briefing-vault
Initialize, manage, and search the per-project .briefing/ vault. Obsidian-compatible persistent knowledge base.