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 ash1794/vibe-engineering --skill vibe-workstream-orchestrationgit clone --depth 1 https://github.com/ash1794/vibe-engineeringWrote 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/ash1794/vibe-engineering/vibe-workstream-orchestration)<a href="https://agentmods.dev/skills/ash1794/vibe-engineering/vibe-workstream-orchestration"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-workstream-orchestration/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/ash1794/vibe-engineering/vibe-workstream-orchestration"><img src="https://agentmods.dev/badge/skills/ash1794/vibe-engineering/vibe-workstream-orchestration.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 | $0.00115 | $0.01031 |
| Opus 5.5 | $0.00046 | $0.00412 |
| Sonnet 5.5 | $0.00023 | $0.00206 |
| Haiku 4.5 | $0.00012 | $0.00103 |
Grade A, and why
vibe-workstream-orchestration 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 20d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibe-workstream-orchestration
vibe-parallel-task-decomposition answers "what can run at once?" This skill answers the next question: who owns what for the rest of the project, and what does the main thread do while they work? The main thread plans, routes and verifies. If it starts building, its context fills with detail and parallelism collapses. If it delegates reactively, every request becomes a new agent that needs a fresh brief, and nobody owns the result.
When to Use This Skill
- A build runs over several phases (build, review, fix, QA) with three or more agents at once
- The task list is filling with agents that did one thing (commit, fix one CI failure, write a PR description)
- Agents are colliding: the same files, the same port, a branch moved under someone
- The main thread's context is filling with build output instead of decisions
When NOT to Use This Skill
- One agent can do the work in one sitting
- A one-shot fan-out with no follow-ups (use
vibe-parallel-task-decomposition) - The work is all in one file or in tightly coupled files
- The harness can't message a running agent (define streams anyway, but expect to re-brief)
Steps
-
Define workstreams by file ownership. Use three to eight streams, each owning a set of paths end to end. For each stream, write down: paths owned, acceptance criteria, gates it must pass, and paths it must not touch. Shared files (global styles, layout, config) get exactly one owner; other streams request changes to them through the orchestrator.
-
Record the base. Note the base commit SHA and branch for the phase. Each writing stream gets its own worktree (or clone) from that base. Read-only agents (reviewers, auditors) can share one.
-
Brief once, for the whole phase. Each brief contains the ownership map, the gates, the commit rule ("rebase onto the remote branch, rebuild, run gates, then push; never force"), and a bounded report format. Ask for conclusions, not file dumps.
-
Owners do the whole loop. Each stream builds, verifies, commits and pushes its own work. Don't spawn separate committer, fixer, or description-writer agents.
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.
- 20d ago First seen · 60 lines · 115 tokens per session scan A 7c252230d051
vibe-workstream-orchestration is a skill published in the GitHub repository ash1794/vibe-engineering (164 stars, last pushed 11d ago), licensed MIT. It adds 115 tokens to every session and 1,031 once invoked, about $0.0005 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 2026-09-29.
Other skills, from other repositories
contract-testing-flywheel
Generate a structured onboarding backlog — in Jira, GitHub Issues/Projects, Azure DevOps, or as a manual markdown export — that drives a development team from zero to publishing both consumer and provider contract tests. Use when the user invokes /contract-testing-flywheel or asks to "kick off contract testing for a…
cherry-regression-test
Run Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.
agent-notes
Use when deciding whether a Cherry Studio change needs an Agent Note, authoring or reviewing a Spec, recording a durable bug-fix decision, moving a note between proposed/implemented/rejected, or checking supersession and stacked Spec approval.
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
req-analyze
A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.
feature-verify
Feature verification (READ-ONLY, P0-P5). Use when: verifying feature behavior after deployment, validating API responses, diagnosing production issues, post-deploy smoke test. Not for: modifying data (use feature-dev), code review (use codex-review-fast), writing tests (use codex-test-gen), security audit (use…