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 composergit 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/composer)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/composer"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/composer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00055 | $0.02161 |
| Opus 5 | $0.00028 | $0.01081 |
| Sonnet 5 | $0.00011 | $0.00432 |
| Haiku 4.5 | $0.00006 | $0.00216 |
Grade A, and why
composer 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 8d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The composer is the agent-hosted control plane for turning raw ideas into routed, approved specifications — without ever building. It is the interactive front half of the flywheel:
operator idea ─▶ [COMPOSER: route → DECIDE → spec PR → nudge]
│ merged spec PR
▼
[DAEMON: build the merged spec]
Inside a live supported host-agent session, Claude Code invokes /composer; Codex invokes
$composer. The ai-conductor compose terminal launcher is a Claude-only launcher: it opens
an interactive claude /composer session. Native persistent-session launch and recovery for other
hosts is deferred to #759; do not imply that this launcher creates a Codex session.
This is the idea→plan loop, not the execution loop. The per-repo daemon scans merged spec PRs
and builds them; the only coupling is the merged spec PR and a fire-and-forget ensureRunning
nudge. The composer never drives, waits on, or owns the daemon.
The loop needs real skills, agent personas, and hooks (/explore, /prd, /stories, /plan), so
the composer is the supported host agent: it calls deterministic ai-conductor compose primitives
for registry reads, guarded commits, PR opening, and daemon nudges, and runs DECIDE skills in chat.
Boundaries
- Never build, never merge. The composer opens spec PRs; the operator merges them; the daemon
builds them. Do not run
/pipeline,/tdd,conduct(build mode), orgh pr merge. - Route artifacts to the target repo, never the composer's cwd.
AuthoringGuardenforces this. - Author in a per-idea worktree, never the primary checkout. Authoring,
land, andhandoffuse<target>/.worktrees/engineer-<slug>; never fall back to the shared checkout. - One idea at a time, operator-gated at every fork. Confirm routing, create-on-no-fit, and each DECIDE output. Never assume.
The Loop
Handle exactly ONE idea per session, then end. File-backed registry, lessons, and processed
markers let the next fresh supported host-agent session recover the durable state. The Claude-only
launcher (ai-conductor compose) relaunches Claude Code with clean context; other-host persistent
session launch/recovery remains deferred to #759.
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.
- 8d ago First seen · 154 lines · 55 tokens per session scan A bf7643e0b543
composer is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 2,161 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.