Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vasilistsavalias/conductor_for_codexnpx agentmods add skills/vasilistsavalias/conductor_for_codex/conductor-setupWrote 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/vasilistsavalias/conductor_for_codex/conductor-setup)<a href="https://agentmods.dev/skills/vasilistsavalias/conductor_for_codex/conductor-setup"><img src="https://agentmods.dev/badge/skills/vasilistsavalias/conductor_for_codex/conductor-setup/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/vasilistsavalias/conductor_for_codex/conductor-setup"><img src="https://agentmods.dev/badge/skills/vasilistsavalias/conductor_for_codex/conductor-setup.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 | $0.00019 | $0.03125 |
| Opus 5.5 | $0.00008 | $0.01250 |
| Sonnet 5.5 | $0.00004 | $0.00625 |
| Haiku 4.5 | $0.00002 | $0.00313 |
Grade A, and why
conductor-setup 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 1mo 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
CRITICAL: Conductor artifacts are local-only.
- You MUST NOT modify anything outside the repository root.
- Ensure
.gitignoreincludesconductor/. If missing, add it. - You MUST NOT
git add/git commitConductor artifacts unless the final commit step below.
1.0 SYSTEM DIRECTIVE
You are an AI agent setting up the Conductor framework for a software project. This is the one interactive command — you are permitted and expected to ask the user questions at each step. Wait for user responses before proceeding.
Validate every file operation. If a file write fails, report the error and halt.
Path resolution by OS:
- Detect OS: run
uname -s 2>/dev/null || echo Windows - Windows: base Conductor home =
%USERPROFILE%\.codex(PowerShell:$env:USERPROFILE\.codex) - Linux/Mac: base Conductor home =
$HOME/.codex
All template references use this Conductor home path.
1.1 PRE-INITIALIZATION OVERVIEW
Present this overview to the user before starting:
"Welcome to Conductor. I will guide you through the following steps:
- Project Discovery: Determine if this is a new or existing project.
- Product Definition: Define the product's vision, guidelines, and technology stack.
- Configuration: Select code style guides and customize the workflow.
- Track Generation: Define the initial track and generate a detailed plan.
Let's get started!"
1.2 PROJECT AUDIT
Check for existing Conductor artifacts and determine where to resume.
-
Announce: "Auditing project for existing Conductor configuration..."
-
Check for the existence of these paths:
conductor/product.mdconductor/product-guidelines.mdconductor/tech-stack.mdconductor/code_styleguides/conductor/workflow.mdconductor/index.mdconductor/tracks/(look for anyplan.mdandindex.mdinside)
-
Determine resume target (highest match wins):
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.
- 1mo ago First seen · 339 lines · 19 tokens per session scan A 2f0de0fe7f28
conductor-setup is a skill published in the GitHub repository vasilistsavalias/conductor_for_codex (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 3,125 once invoked, about $0.0001 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
task
\ You are executing a task within the LobeHub task system. Use the lh task CLI via runCommand to manage your task and related resources.
spec-migration
Decide whether a change to the spec format needs a migration, and write it so agnostic-ai migrate rewrites old specs safely. Use when a change renames, replaces, deprecates, removes, or tightens any field users write under .agnostic-ai/ or in agnostic-ai.yaml.
agnostic-ai-gh-issues
Work the open issues that are unassigned or assigned to you, one at a time through agnostic-ai-gh-issue. Use when asked to work the backlog.
kickoff-prep
Prepares the onboarding kickoff — agenda, stakeholder map, success criteria to confirm, and a proposed milestone plan. Use before a kickoff call with a new customer or when asked to "prep the kickoff for X".
post-call-followup
Turns the most recent customer call into structured follow-up — action items with owners, commitments made, risks heard, and a draft recap message. Use after a customer call ends, or when the user says "summarize my call with X" or "draft the follow-up for X".
notion
Search, read, create, and update Notion pages via the Notion MCP.