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 instructions/shaahink/conductor/agents-mdgit clone --depth 1 https://github.com/shaahink/conductorWhat 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 | $0.07172 | $0.07172 |
| Opus 5 | $0.03586 | $0.03586 |
| Sonnet 5 | $0.01434 | $0.01434 |
| Haiku 4.5 | $0.00717 | $0.00717 |
Grade A, and why
conductor AGENTS.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
real `HttpListener` on a real loopback port — curl it or point `face-go --url` at it directly. How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — what a session needs to know before it edits anything
Current state only. The append-only stack of nine superseded ## Resume here sections that used to
live here is archived verbatim at
docs/history/handoffs/AGENTS-resume-log-2026-07.md
— nothing was deleted, it was moved so that this file is short enough to actually be read.
What this is
Conductor is an autonomous multi-session engineering orchestrator (C# / .NET 10). It spawns headless
agent sessions, verifies their work independently (gate battery + git commits + tracker diff + a
Verifier pass), is fully resumable, and reports to .conductor/REPORT.md. It drives itself: every era
of this repo since Baton has been built by Conductor running a plan against Conductor.
The Face is face-go/ — a Go + Bubble Tea TUI over the engine's HTTP+SSE control plane. It is a
disposable client: the run outlives it. (The TypeScript + Ink face was retired in Maestro M7; its
history is in git, do not re-add it.)
The architecture map is ARCHITECTURE.md — the assemblies and the one allowed
dependency direction, a session's lifecycle end to end, the seams, the two surfaces, the
file-organisation convention, and a "where do I add X" table. Read it before your first edit.
The live era: Karvan
The active plan is Karvan core — the engine knows what it did and what it cost.
| Spec | docs/history/CONDUCTOR-KARVAN.md (mission, per-stage acceptance) |
| Plan | plans/karvan/core.plan.json |
| Tracker | plans/karvan/CORE-TRACKER.md — the ## Handoff block is the whole handover between sessions |
| Branch | feat/karvan |
Era artefacts live one folder per era, as plans/karvan/ does. Closed-era trackers are under
docs/history/trackers/; closed-era specs under docs/history/.
Read order for a fresh session
ARCHITECTURE.md— the map, and the file-organisation convention reviewers cite.plans/karvan/CORE-TRACKER.md,## Handoffblock — what the last session left you.- Your stage's section of
docs/history/CONDUCTOR-KARVAN.md— that section, not the whole document. docs/operating.md— driving a live run: commands, steering, the control plane, escalation.- This file's standards sections below, before you write C#;
face-go/STYLE.mdbefore you touch the Face.
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 · 371 lines · 7,172 tokens per session scan A 225a866684d6
conductor AGENTS.md is an instructions file published in the GitHub repository shaahink/conductor (5 stars, last pushed 5d ago), licensed MIT. It adds 7,172 tokens to every session, about $0.0359 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
maui performance-hotpaths.instructions.md
Instructions for dotnet/maui, covering performance-critical path rules, hot paths in maui, allocation avoidance, caching and invalidation and collection iteration.
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
moorestech AGENTS.md
AGENTS.md instructions for moorestech/moorestech, covering コーディングの指針, qa（必須）, 互換性とパフォーマンス, 既知の制約（設計上の割り切り） and regionの活用.
Fluence.Wpf AGENTS.md
AGENTS.md instructions for sintaxasn/Fluence.Wpf, covering fluence.wpf - developer handbook, 1. project overview, solution layout, clr namespaces and 2. coding standards.
a-i--skills 03-development-workflow.instructions.md
Instructions for organvm-iv-taxis/a-i--skills, covering development workflow instructions, no repo-wide build system, common development commands, after adding/modifying skills and validation before committing.