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 jstoup111/ai-conductor --skill pipelinegit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/pipeline)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/pipeline"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/pipeline/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/jstoup111/ai-conductor/pipeline"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.09150 |
| Opus 5.5 | $0.00013 | $0.03660 |
| Sonnet 5.5 | $0.00007 | $0.01830 |
| Haiku 4.5 | $0.00003 | $0.00915 |
Grade A, and why
pipeline scanned grade A with 1 finding 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 3d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
already active. The operator raises N with `[agents] max_threads` in `~/.codex/config.toml`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Orchestrates execution of an implementation plan through quality-gated stages. The configured harness runner drives the task loop — it parses the plan, iterates tasks, and sends one prompt per task. The selected host agent orchestrates each task by dispatching implementers through its available subagent facility. Subagent context is isolated and discarded after completion, keeping the orchestrator's context lean.
Execution Model
Harness runner Host agent (orchestrator) Subagent (implementer)
────────────── ───────────────────── ──────────────────────
Parse plan, extract task → Receive task context → Full TDD cycle
Dispatch subagent → RED → DOMAIN → GREEN
Verify result ← → DOMAIN → COMMIT
Check task-status.json ← Report PASS/FAIL (context discarded)
Next task
Key constraint: The selected host agent MUST dispatch implementers through its available subagent facility. It must NOT implement directly in the orchestration session. This keeps the orchestrator's context bounded to ~2-3 summary lines per task regardless of feature size.
Host mechanics: Claude Code uses its Agent tool and Claude model labels for this delegation.
Pi has no native facility; with llm_providers.pi.subagents: true the engine loads the
pi-subagents extension, and the orchestrator delegates each task with one
subagent({ agent: "delegate", task: <dispatch prompt>, async: false }) call. Never shell out to
pi to delegate: a nested process runs outside the engine's model, sandbox, and accounting.
Other supported hosts use their native equivalent. These mechanics may differ, but they MUST
preserve the shared task scope, TDD cycle, task attribution, verification, review, and gate
contracts below.
Practices
Execution Mode
There is one mode. The human reviews at batch boundaries; the agent runs quality gates on every task and dispatches independent tasks in parallel, up to X at a time (see Parallel Execution).
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.
- 3d ago Changed · -9 lines · +2 tokens per session 064b3e5f691f
- 6d ago Changed · +11 lines 961e9346a606
- 14d ago Changed · -122 lines 137e0f136312
- 16d ago Changed 359bf9bed035
- 18d ago Changed · +4 lines 09dd49198011
- 22d ago Changed · +4 lines 1767b933cb2a
- 23d ago Changed · +3 lines 1e14a4d0f1a8
- 26d ago Changed · +12 lines f563b384002a
- 28d ago Changed · +1 lines 0ee195c45959
- 1mo ago First seen · 748 lines · 31 tokens per session scan A 1c6bb68816dd
pipeline is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 9,150 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…