A method for organizing coding work around project context, written specifications, implementation plans, and progress tracking. TDD, or test-driven development, means writing tests before or alongside the code they check.

Use it in projects with a conductor/ directory to plan features, bugs, and improvements, execute phased work, track progress, and coordinate independent tasks.

It reduces guesswork by making the project's goals, technical constraints, workflow, and active tasks explicit before implementation begins.

How NguyenSiTrung/Conductor-Beads configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to NguyenSiTrung/Conductor-Beads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/NguyenSiTrung/Conductor-Beads/main/.claude/skills/conductor/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/NguyenSiTrung/Conductor-Beads

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nguyensitrung/conductor-beads/conductor/github.svg)](https://agentmods.dev/skills/nguyensitrung/conductor-beads/conductor)

Your own site

<a href="https://agentmods.dev/skills/nguyensitrung/conductor-beads/conductor"><img src="https://agentmods.dev/badge/skills/nguyensitrung/conductor-beads/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nguyensitrung/conductor-beads/conductor"><img src="https://agentmods.dev/badge/skills/nguyensitrung/conductor-beads/conductor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,056 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00179	$0.02056
Opus 5	$0.00089	$0.01028
Sonnet 5	$0.00036	$0.00411
Haiku 4.5	$0.00018	$0.00206

Measured 11d ago against content hash 970708fb748e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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 11d 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.

.claude/skills/conductor/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor: Context-Driven Development

Measure twice, code once.

Overview

Conductor enables context-driven development by:

Establishing project context (product vision, tech stack, workflow)
Organizing work into "tracks" (features, bugs, improvements)
Creating specs and phased implementation plans
Executing with TDD practices and progress tracking
Parallel execution of independent tasks using sub-agents

For parallel execution details (annotations, state schema, when to use), see references/workflows.md.

Context Loading

When this skill activates, load these files to understand the project:

conductor/product.md - Product vision and goals
conductor/tech-stack.md - Technology constraints
conductor/workflow.md - Development methodology (TDD, commits)
conductor/tracks.md - Current work status
conductor/patterns.md - Codebase patterns (read before starting work)

Important: Conductor commits locally but never pushes. Users decide when to push to remote.

For active tracks, also load:

conductor/tracks/<track_id>/spec.md
conductor/tracks/<track_id>/plan.md
conductor/tracks/<track_id>/learnings.md - Patterns/gotchas from this track

Learnings System (Ralph-style)

Conductor captures and consolidates learnings across tracks. For full details, see references/learnings-system.md.

Key Files

conductor/patterns.md - Project-level consolidated patterns
conductor/tracks/<id>/learnings.md - Per-track discoveries

Templates

references/patterns-template.md - Full patterns.md template
references/learnings-template.md - Full learnings.md template

Knowledge Flywheel

Capture - After each task, append to track's learnings.md
Elevate - At phase/track completion, promote reusable patterns to patterns.md
Archive - Extract remaining patterns before archiving
Inherit - New tracks read patterns.md to prime context

Read the full file on GitHub · 154 lines

Files

What ships with it

22 files 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.

Changes

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.

11d ago First seen · 154 lines · 179 tokens per session scan A 970708fb748e

Subscribe to this mod's changes

conductor is a skill published in the GitHub repository NguyenSiTrung/Conductor-Beads (24 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 179 tokens to every session and 2,056 once invoked, about $0.0009 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.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

Conductor-Beads: Skill for Claude Code