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 skills add robertbarclayy/conducty --skill conducty-bootstrapgit 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/skills/robertbarclayy/conducty/conducty-bootstrap)<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-bootstrap"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-bootstrap.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 | $0.00089 | $0.01333 |
| Opus 5 | $0.00044 | $0.00666 |
| Sonnet 5 | $0.00018 | $0.00267 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
conducty-bootstrap 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 7d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conducty Bootstrap — First-Run Walkthrough
The fastest path from "just installed" to "first finished plan." Bootstrap is opinionated: it picks a small first goal so the user sees the entire cycle (Plan → Execute → Verify → Improve) without committing to anything ambitious.
[!important] One-shot skill Bootstrap is meant to run once per machine. After it completes, the cycle is self-sustaining via [[conducty-plan]].
When to Use
- The user just ran
install-claude-code.shand is starting their first session - The user says "set up Conducty", "first time", "get started", "bootstrap"
- A
Glob Plans/Plan *.mdagainst the vault returns zero results — auto-trigger this skill
Workflow
Step 1: Confirm the Vault
Resolve $CONDUCTY_VAULT (default ~/Obsidian/Conducty/). Confirm with the user:
"Conducty vault is at
<resolved path>. Open this directory in Obsidian to navigate the graph as we build it. OK to proceed?"
If the user wants a different path, ask them to set $CONDUCTY_VAULT in their shell profile and re-run. Do not silently move the vault.
Step 2: Seed Missing Indexes + Accumulators
Use [[conducty-obsidian]]'s bootstrap section. Create any missing:
- Indexes:
Conducty Index,Plans Index,Designs Index,Context Index,Improvements Index - Accumulators:
Failure Patterns,Metrics,Prompt Log
If the installer already seeded them, this is a no-op.
Step 3: First Project — Ingest Context
Ask:
"Which project would you like Conducty to start with? Give me the path."
Run [[conducty-context]] on that path. The output is the project sub-graph: hub, Architecture, Conventions, Invariants, Hotspots, Tests, Glossary.
Briefly summarize for the user: bounded contexts found, test command resolved, any concerns flagged.
Step 4: Pick a Tiny First Goal
Suggest a Low-complexity goal — something the user will see succeed inside 30 minutes. Examples:
- "Add a small utility function with TDD" (writes one function + tests)
- "Improve a single error message in module X"
- "Write a test for a previously-untested branch"
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.
- 7d ago First seen · 125 lines · 89 tokens per session scan A d87d4a45b75f
conducty-bootstrap is a skill published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,333 once invoked, about $0.0004 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.
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…
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…
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…
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…