ai-conductor: Skill for Claude Code

.agents/skills/event-spine/SKILL.md

event-spine is a skill for Claude Code, Codex from jstoup111/ai-conductor. It costs 208 tokens per session (2,077 once invoked), scanned A, original, Apache-2.0.

A design check for adding ways to observe, report, or coordinate work in the ai-conductor repository. It directs those additions through the repository's existing event path, which records events and makes them available to its consumers.

In plain words
What is it for?
Use it before adding a watcher, poller, sidecar file, ad-hoc log, timestamped artifact, or event type. It helps determine how the new behavior should extend the existing event system.
Why use it?
It prevents separate logs, watcher files, polling paths, or telemetry channels from becoming competing sources of information. Such parallel paths may be invisible to existing tools.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is jstoup111/ai-conductor's own configuration. It tells Claude Code and Codex how to work on ai-conductor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-conductor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jstoup111/ai-conductor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jstoup111/ai-conductor/main/.agents/skills/event-spine/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jstoup111/ai-conductor

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for event-spine

README.md
[![agentmods](https://agentmods.dev/badge/skills/jstoup111/ai-conductor/event-spine/github.svg)](https://agentmods.dev/skills/jstoup111/ai-conductor/event-spine)
Your own site
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/event-spine"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/event-spine/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.

agentmods 80×15 button for event-spine

Your own site · 80×15
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/event-spine"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/event-spine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 208 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,077 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00208 $0.02077
Opus 5 $0.00104 $0.01038
Sonnet 5 $0.00042 $0.00415
Haiku 4.5 $0.00021 $0.00208

Measured 11d ago against content hash 74f4ad3680dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

event-spine 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 11d 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.

.agents/skills/event-spine/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Event Spine

Extend the existing event spine; never add a parallel channel.

This repository has exactly one telemetry spine. Every mechanism that observes, reports, or coordinates work is expected to ride it. A design that invents a second channel for a concern the spine already carries is a defect at design time, not a style preference — and it is the specific mistake this skill exists to catch, because it is invisible in review and expensive to unwind.

Run this before the design is written down, not after. The cost of the check is one question; the cost of missing it is a permanent second source of truth.


1. The spine

ConductorEventEmitter
  → the ConductorEvent union (src/conductor/src/types/events.ts)
    → EventPersister (src/conductor/src/engine/event-persister.ts)
      → .pipeline/events.jsonl

Consumers subscribe to the emitter or read the ledger: the daemon and its CLI, the UI renderer and subscriber, the OTel visualizer, and the event sinks. Do not hard-code that list into a design document — grep for it when you need it. The point is not who reads today, it is that everything that reads, reads here. A channel outside this path is seen by none of them.


2. Decision procedure

Answer in order. The first YES that survives step 3 settles it.

Step 1 — Is the thing you are adding a channel?

You are adding a channel if the design introduces any of these:

  • a watcher or poller that observes state to infer that something happened
  • a sidecar file, a bespoke log, or a second ledger with its own format
  • a timestamp, counter, or status stamped into an artifact so a later reader can reconstruct timing
  • an IPC path, a status endpoint, or any out-of-band signal between components

If none of those, this skill does not apply. Stop.

Step 2 — Does the bus already carry this concern?

Ask it literally: is this an occurrence in time that some component needs to know about? If yes, the bus carries it, whether or not a variant for it exists today. A missing variant is not evidence that the bus is the wrong mechanism — it is the work.

Read the full file on GitHub · 173 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 173 lines · 208 tokens per session scan A 74f4ad3680dd

Subscribe to this mod's changes

event-spine is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 208 tokens to every session and 2,077 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens