Borrowing it
Nothing to install: this file belongs to NguyenSiTrung/Conductor-Beads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NguyenSiTrung/Conductor-Beads/main/.claude/commands/conductor-newtrack.mdgit clone --depth 1 https://github.com/NguyenSiTrung/Conductor-BeadsWrote 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/commands/nguyensitrung/conductor-beads/conductor-newtrack)<a href="https://agentmods.dev/commands/nguyensitrung/conductor-beads/conductor-newtrack"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/conductor-newtrack/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/commands/nguyensitrung/conductor-beads/conductor-newtrack"><img src="https://agentmods.dev/badge/commands/nguyensitrung/conductor-beads/conductor-newtrack.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 | $0.00011 | $0.03709 |
| Opus 5 | $0.00005 | $0.01854 |
| Sonnet 5 | $0.00002 | $0.00742 |
| Haiku 4.5 | $0.00001 | $0.00371 |
Grade C, and why
conductor-newtrack scanned grade C 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 12d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- SYSTEM DIRECTIVE: You are an AI agent for the Conductor framework. CRITICAL: Validate every tool call. If any fails, halt and announce the failure. --> Copies of this mod
1 near-identical copy found in the catalogue:
- newtrack — 97% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conductor New Track
Create a new track for: $ARGUMENTS
1.0 SETUP CHECK
PROTOCOL: Verify Conductor environment is properly set up.
-
Check Required Files: Verify existence of:
conductor/product.mdconductor/tech-stack.mdconductor/workflow.md
-
Handle Missing Files:
- If ANY missing: HALT immediately
- Announce: "Conductor is not set up. Please run
/conductor-setupfirst." - Do NOT proceed.
2.0 NEW TRACK INITIALIZATION
2.1 Get Track Description and Determine Type
-
Load Project Context: Read
conductor/directory files. -
Get Track Description:
- If
$ARGUMENTSprovided: Use it as track description - If empty: Ask:
"Please provide a brief description of the track (feature, bug fix, chore, etc.) you wish to start." Wait for response.
- If
-
Infer Track Type: Analyze description to classify as "Feature" or "Something Else" (Bug, Chore, Refactor). Do NOT ask user to classify.
2.2 Interactive Specification Generation (spec.md)
-
Announce:
"I'll now guide you through questions to build a comprehensive
spec.mdfor this track." -
Questioning Phase (3-5 questions):
Question Classification - CRITICAL:
-
1. Classify Question Type: Before EACH question, classify as:
- Additive: For brainstorming/scope (users, goals, features) - allows multiple answers
- Exclusive Choice: For singular commitments (specific technology, workflow rule) - single answer
-
2. Formulate Based on Classification:
- If Additive: Open-ended question + options + "(Select all that apply)"
- If Exclusive Choice: Direct question, do NOT add multi-select
-
3. Interaction Flow:
- CRITICAL: Ask ONE question at a time. Wait for response before next question.
- Last option for every question MUST be "Type your own answer"
- Confirm understanding by summarizing before moving on
-
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.
- 12d ago First seen · 401 lines · 11 tokens per session scan C 112933bf7b6c
conductor-newtrack is a command published in the GitHub repository NguyenSiTrung/Conductor-Beads (24 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 3,709 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.