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.
npx agentmods add skills/shaahink/conductor/run-conductornpx skills add shaahink/conductor --skill run-conductorgit clone --depth 1 https://github.com/shaahink/conductorWrote 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/shaahink/conductor/run-conductor)<a href="https://agentmods.dev/skills/shaahink/conductor/run-conductor"><img src="https://agentmods.dev/badge/skills/shaahink/conductor/run-conductor.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.03011 |
| Opus 5 | $0.00036 | $0.01505 |
| Sonnet 5 | $0.00014 | $0.00602 |
| Haiku 4.5 | $0.00007 | $0.00301 |
Grade A, and why
run-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 5d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conductor is a long-running .NET orchestrator (conductor.exe, a Spectre.Console CLI) that spawns
agent sessions to drive a mega-plan, plus an optional Go/Bubble-Tea companion TUI (face-go).
You cannot smoke-test the engine against a real agent without spending model tokens — so the agent
path here is .claude/skills/run-conductor/driver.ps1, which stands in the token-free fake agent
(tools/fake-agent.ps1) and drives the real engine through a full session loop against a throwaway
repo, then asserts on the result.
All paths below are relative to the repo root (C:\code\conductor-baton). This is a Windows /
PowerShell project (SQLite run.db, PowerShell gates, .exe outputs) — commands are PowerShell,
not bash.
Prerequisites
- .NET SDK 10 (
dotnet --version→10.0.301here) — builds/runs the engine. - Go 1.26+ (
go version→go1.26.5 windows/amd64) — only needed to build theface-goTUI. - git on PATH — the engine shells out to it, and the driver scaffolds a scratch repo.
No agent CLI (opencode/claude) is needed for the driver — that is the whole point of the fake agent.
Build
Engine only (fast, what the driver uses by default — produces
src\Conductor\bin\Debug\net10.0\conductor.exe):
dotnet build src\Conductor\Conductor.csproj -c Debug --nologo -v q
Full install (Release publish of the engine and the Go face, then a conductor shim on PATH):
powershell -File tools\install.ps1
Face only:
cd face-go ; go build -o bin\conductor-face.exe .\cmd\conductor-face\
Run (agent path) — the driver
One command builds the engine if needed, scaffolds a hermetic scratch repo + toy plan + tracker,
runs doctor → run --dry-run → the real run --headless loop (fake agent) → status, and prints
a PASS/FAIL summary. No network, no model calls, no touching the real plans/.
powershell -NoProfile -ExecutionPolicy Bypass -File .claude\skills\run-conductor\driver.ps1
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.
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.
- 5d ago First seen · 200 lines · 72 tokens per session scan A c0af3463153d
run-conductor is a skill published in the GitHub repository shaahink/conductor (5 stars, last pushed 9d ago), licensed MIT. It adds 72 tokens to every session and 3,011 once invoked, about $0.0004 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.
Other skills, from other repositories
cratis-command
Step-by-step guidance for creating a Cratis Arc command — [Command] record, Handle() method, CommandValidator, proxy generation, and React .use() hook with CommandDialog. Use when adding or creating a command, wiring up a form or button to the backend, working with IEventLog, CommandResult, CommandValidator…
ship-changes
Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, prepare no-effect dispositions for related issues, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or…
ship-changes
Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, close the issues it resolves, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or land changes.
auth-and-identity
Use this skill for authentication, authorization, or identity in a Cratis Arc project — backend, frontend, or both. Covers identity providers (IProvideIdentityDetails), protecting commands/queries with authorization attributes, Microsoft Identity Platform, connecting backend identity to React, multi-tenant identity…
cratis-react-page
Step-by-step guidance for building a React page in a Cratis Arc application — DataPage lists, CommandDialog toolbar actions, confirmation and busy-indicator dialogs, row selection, details components, observable queries, and MVVM. Use when building or modifying a page that lists/displays data, adding a table, wiring…
cratis-readmodel
Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…