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.
git clone --depth 1 https://github.com/ckorhonen/claude-skillsWrote 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/ckorhonen/claude-skills/install-conductor)<a href="https://agentmods.dev/commands/ckorhonen/claude-skills/install-conductor"><img src="https://agentmods.dev/badge/commands/ckorhonen/claude-skills/install-conductor/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/ckorhonen/claude-skills/install-conductor"><img src="https://agentmods.dev/badge/commands/ckorhonen/claude-skills/install-conductor.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 | $0.01019 |
| Opus 5 | $0.00005 | $0.00509 |
| Sonnet 5 | $0.00002 | $0.00204 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
install-conductor 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Conductor
Generate a conductor.json file for this project based on detected project type and configuration.
Project Detection
Package Manager Detection
- package-lock.json: !
ls package-lock.json 2>/dev/null && echo "npm detected" - yarn.lock: !
ls yarn.lock 2>/dev/null && echo "yarn detected" - bun.lockb: !
ls bun.lockb 2>/dev/null && echo "bun detected" - pnpm-lock.yaml: !
ls pnpm-lock.yaml 2>/dev/null && echo "pnpm detected"
Project Type Detection
- package.json: !
cat package.json 2>/dev/null | head -50 - pyproject.toml: !
cat pyproject.toml 2>/dev/null | head -30 - requirements.txt: !
ls requirements.txt 2>/dev/null && echo "Python pip project" - go.mod: !
cat go.mod 2>/dev/null | head -10 - Cargo.toml: !
cat Cargo.toml 2>/dev/null | head -20
Environment Files
- .env.example: !
ls .env.example .env.sample .env.template 2>/dev/null | head -1
Existing conductor.json
!cat conductor.json 2>/dev/null && echo "--- conductor.json already exists ---"
Instructions
Based on the detection above, create a conductor.json file in the project root.
conductor.json Format
{
"scripts": {
"setup": "commands to install dependencies and set up environment",
"run": "command to start the dev server or main process",
"runScriptMode": "nonconcurrent"
}
}
Script Guidelines
Setup Script - Runs when workspace is created:
- Install dependencies using the detected package manager
- If .env.example exists, copy it:
cp .env.example .env - Chain commands with
;(e.g.,npm install; cp .env.example .env)
Run Script - Triggered by the "Run" button:
- For web servers, use
$CONDUCTOR_PORTenvironment variable - Look at available scripts in package.json (dev, start, serve)
- Prefer dev/development scripts over production scripts
runScriptMode - Set to "nonconcurrent" for dev servers (kills previous before starting new)
Framework-Specific Port Flags
| Framework | Run Command |
|---|---|
| Next.js | npm run dev -- -p $CONDUCTOR_PORT |
| Vite | npm run dev -- --port $CONDUCTOR_PORT |
| Create React App | PORT=$CONDUCTOR_PORT npm start |
| Express | Assumes app reads process.env.PORT or $CONDUCTOR_PORT |
| Python Flask | flask run --port $CONDUCTOR_PORT |
| Python FastAPI | uvicorn main:app --port $CONDUCTOR_PORT |
| Go | go run . --port $CONDUCTOR_PORT or set env |
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 · 107 lines · 11 tokens per session scan A 086aded12502
install-conductor is a command published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 1,019 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 commands, from other repositories
run-powershell
Execute a PowerShell script on an Atera agent.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
restore-check
Restore-readiness check - has this actually been restore-tested, for one client or the whole portfolio.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
update-ticket
Update fields on an existing Atera ticket.
backup-status
Portfolio-wide backup job health snapshot - failure count, at-risk clients, and storage trends.