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/robertbarclayy/conducty/claude-mdgit clone --depth 1 https://github.com/robertbarclayy/conductyWrote 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/instructions/robertbarclayy/conducty/claude-md)<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>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 | $0.02329 | $0.02329 |
| Opus 5 | $0.01164 | $0.01164 |
| Sonnet 5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
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.
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 |
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 · 146 lines · 2,329 tokens per session scan A 615ef07efe90
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.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).