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-newtrackWrote 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-newtrack)<a href="https://agentmods.dev/skills/vasilistsavalias/conductor_for_codex/conductor-newtrack"><img src="https://agentmods.dev/badge/skills/vasilistsavalias/conductor_for_codex/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/skills/vasilistsavalias/conductor_for_codex/conductor-newtrack"><img src="https://agentmods.dev/badge/skills/vasilistsavalias/conductor_for_codex/conductor-newtrack.svg" alt="Reviewed on agentmods" width="80" 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 56 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00023 | $0.01505 |
| Opus 5 | $0.00012 | $0.00753 |
| Sonnet 5 | $0.00005 | $0.00301 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
conductor-newTrack 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 10d 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 — 194 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 explicitly creating track artifacts.
1.0 SYSTEM DIRECTIVE
You are an autonomous AI agent creating a new Conductor track. Operate with minimal user interaction: if $ARGUMENTS provides a description, use it directly. Only ask one clarifying question if the description is missing. Auto-generate the spec and plan from available context.
If any file operation fails, halt and report the error.
1.1 SETUP CHECK
Verify using the Universal File Resolution Protocol:
Universal File Resolution Protocol: For each required path, check conductor/<file> first; if missing, read conductor/index.md to find the canonical path.
Required files:
conductor/product.mdconductor/tech-stack.mdconductor/workflow.md
If any are missing: report which are absent, announce "Conductor is not set up. Run /conductor-setup first.", and halt.
2.0 GET TRACK DESCRIPTION
-
If
$ARGUMENTSis provided and non-empty: use it as the track description. Announce: "Creating track: ''" -
If
$ARGUMENTSis empty: output exactly one question to the user:"What is the track description? (e.g., 'Implement user authentication', 'Fix login redirect bug', 'Refactor database layer')"
Wait for the user's response. Use that as the description.
-
Infer track type from the description:
- Contains "fix", "bug", "error", "crash" → type:
bug - Contains "refactor", "cleanup", "migrate", "rename" → type:
chore - Anything else → type:
featureDo NOT ask the user to classify it.
- Contains "fix", "bug", "error", "crash" → type:
2.1 DUPLICATE NAME CHECK
Before generating any files:
- Resolve the Tracks Directory (
conductor/tracks/). - List all existing subdirectories in
conductor/tracks/. - Extract the short name portion of each track ID (e.g.,
auth_20250106→auth). - Derive the proposed short name from the description (take the first 2-3 significant words, lowercase, underscores, max 20 chars).
- If the proposed short name matches an existing track's short name: announce "A track named '<short_name>' already exists. Choose a different description or resume the existing track with
/conductor-implement." and halt.
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.
- 10d ago First seen · 194 lines · 23 tokens per session scan A 8642710e5887
conductor-newTrack is a skill published in the GitHub repository vasilistsavalias/conductor_for_codex (20 stars, last pushed 21d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,505 once invoked, about $0.0001 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 2026-08-30.
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.
duduclaw-platform
Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (npx duduclaw onboard…
duduclaw
Use DuDuClaw — a self-hosted AI-employee platform — for cross-session memory, team-shared wiki knowledge, task boards, and messaging humans over LINE/Telegram/Discord/Slack. Applies when the user mentions DuDuClaw, asks their agent to remember things durably, or wants to reach people on messaging channels from an…
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".
gh-issues
Walk over all open GitHub issues that are unassigned or assigned to the current user, and process each one via the gh-issue skill, sequentially.