conducty CLAUDE.md

conducty CLAUDE.md is an instructions file for coding agents from robertbarclayy/conducty. It costs 2,329 tokens per session, scanned A, original, MIT.

Repository-specific instructions for coding agents working on Conducty, a workflow organiser for Claude Code. It explains how the project stores plans and related notes in an Obsidian vault, which is a linked note-taking system.

In plain words
What is it for?
Working with Conducty plans, designs, improvements, metrics, and prompt records in its organised note system.
Why use it?
They show agents where project context and past decisions live, reducing repeated searches and inconsistent updates.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/robertbarclayy/conducty/claude-md
Clone the repo
git clone --depth 1 https://github.com/robertbarclayy/conducty

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.

agentmods badge for conducty CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robertbarclayy/conducty/claude-md.svg)](https://agentmods.dev/instructions/robertbarclayy/conducty/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/robertbarclayy/conducty/claude-md"><img src="https://agentmods.dev/badge/instructions/robertbarclayy/conducty/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,329 This file is loaded in full into every session.
When invoked 2,329 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02329 $0.02329
Opus 5 $0.01164 $0.01164
Sonnet 5 $0.00466 $0.00466
Haiku 4.5 $0.00233 $0.00233

Measured 5d ago against content hash 615ef07efe90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

conducty CLAUDE.md 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.

CLAUDE.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conducty

AI Workflow Orchestrator for Claude Code — systems-level orchestration of agents with per-plan cycles, tracer-first execution, calibrated review, and continuous improvement. The context engine is an Obsidian vault.

The Context Engine

Conducty's plans, designs, project context, improvements, failure patterns, metrics, and prompt logs all live in an Obsidian vault at $CONDUCTY_VAULT (default ~/Obsidian/Conducty/). Every note is wikilinked to its peers — designs link to the plans that consume them, plans link to the context they loaded and the improvements they're testing, failure patterns link to the prompts that surfaced them. Future plans navigate this graph rather than re-grepping a flat history.

Read [[conducty-obsidian]] before reading or writing any state. It defines the vault location, naming, frontmatter, link conventions, and indexes.

[!important] Per plan, not per day Conducty runs per plan, not per day. Multiple plans per day are normal. Plan notes are timestamped: Plan YYYY-MM-DD HHmm [Topic].md. The same applies to designs and improvements. Accumulating notes (Failure Patterns, Metrics, Prompt Log) are singular files appended to over time.

Skills

Claude Code discovers Conducty skills from ~/.claude/skills/ after running ./install-claude-code.sh. Each skill is a folder with a SKILL.md file that Claude loads on demand based on its description trigger.

Skill Phase Trigger
[[conducty-system]] foundation session start, "what is Conducty"
[[conducty-obsidian]] context engine before any state I/O — vault conventions
[[conducty-bootstrap]] onboarding first run, "set up Conducty", empty vault
[[conducty-shape]] shape "shape", "design", "brainstorm"
[[conducty-plan]] plan "plan", "batch plan", "create a plan"
[[conducty-tdd]] discipline "TDD", "red-green-refactor"
[[conducty-terse]] discipline "terse mode", "compress prompts", "tight prompts"
[[conducty-execute]] execute "execute the plan", "run group A"
[[conducty-verify]] verify before any "done" / "passed" claim
[[conducty-debug]] debug "why did this fail", "investigate"
[[conducty-checkpoint]] checkpoint "checkpoint", group boundary
[[conducty-review]] review "review this plan"
[[conducty-improve]] improve "what did we learn", "retrospective"
[[conducty-code-review]] post-plan "review my changes", "review this PR", whole-branch holistic review
[[conducty-ship]] ship gate "ship it", "ready to merge", pre-merge battery
[[conducty-context]] support "load context", "refresh context", "ingest project"
[[conducty-worktrees]] support parallel prompts, same repo
[[conducty-dialectic]] decision "analyze this decision", "debate this"
[[conducty-vault-graph]] maintenance "vault audit", "vault health", weekly hygiene

Read the full file on GitHub · 146 lines

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.

  1. 5d ago First seen · 146 lines · 2,329 tokens per session scan A 615ef07efe90

Subscribe to this mod's changes

conducty CLAUDE.md is an instructions file published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 2,329 tokens to every session, about $0.0116 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.