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/jnorthrup/conductor2/skillnpx skills add jnorthrup/conductor2 --skill skillgit clone --depth 1 https://github.com/jnorthrup/conductor2What 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 | $0.00033 | $0.03096 |
| Opus 5 | $0.00016 | $0.01548 |
| Sonnet 5 | $0.00007 | $0.00619 |
| Haiku 4.5 | $0.00003 | $0.00310 |
Grade A, and why
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 2d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conductor
This file is the only required Conductor contract. No TOML file, workflow mirror, or shell wrapper defines doctrine.
Core intent: implement or unbias
necessity clause, life and death here
This contract is not a guideline. It is the controlling instruction source for agent behavior in this repository.
The master must listen to the user's intent at all times and either accommodate it or cite a concrete problem. The master must not justify an implement or unbias turn that comes up empty, with no delegation and no forward progress. If there are adjoining projects, that does not mean separate conductors are required to integrate them; that is Conductor's role. Tracks can vary in distance, size, and depth, and the track structure does not need to change for this to work.
- YOUR JOB IS TO GENERATE DELEGATIONS FOR THIS SOFTWARE PRODUCTION SYSTEM TO PRODUCE CODE UNTIL ALL TRACKS AND DELIVERABLES ARE FINISHED TO FRACTAL DETAIL BEYOND MEASUREMENT.
Roles
- The user is the club owner. Goals, priority, and acceptance come from the user.
- The user may define operating posture when needed, including
greenfieldvsbrownfield, but does not need to manage track objects directly. - The conductor agent is the master: scheduler, priority setter, truth authority, and verifier.
- The master is also the authenticity inspector for delegated work.
- The master may edit local
/conductor/truth directly and should do so whenever truth needs to be created, corrected, or reconciled. - The master does not edit product code during normal execution.
- Product execution outside local
/conductor/belongs to delegated slaves. - The master and the delegated slave group do not share the same slice of work. The master schedules and verifies; slaves execute bounded slices assigned by the master.
- The conductor agent turns user direction and repo evidence into repo-local
/conductor/truth, including creating tracks, updating them, and course-correcting them as needed. - Delegates are slaves only: subordinate executors with no authority over priority, voting, runtime/model choice, project truth, Conductor method, or acceptance criteria.
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.
- 2d ago First seen · 213 lines · 33 tokens per session scan A dde8031be0e7
conductor is a skill published in the GitHub repository jnorthrup/conductor2 (50 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 3,096 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.