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 skills/robertbarclayy/conducty/conducty-shapenpx skills add robertbarclayy/conducty --skill conducty-shapegit 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-shape)<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-shape"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-shape.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 | $0.00058 | $0.02019 |
| Opus 5 | $0.00029 | $0.01009 |
| Sonnet 5 | $0.00012 | $0.00404 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade A, and why
conducty-shape 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 6d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conducty Shape — Appetite, Boundaries, Design
Turn unclear or complex goals into bounded, executable designs. Shaping answers three questions before any prompt is written: How much is this worth? What's in scope? What's explicitly out?
This is not brainstorming in the open-ended sense. Shaping is opinionated — you propose boundaries, cut rabbit holes, and produce a design that fits the declared appetite. The output is a design doc that [[conducty-plan]] can decompose into prompts.
[!warning] Hard gate Do NOT generate prompts for a non-trivial goal until you have presented a design with appetite, scope, and no-go zones, and the user has approved it.
When to Use
Mandatory (invoked by [[conducty-plan]]):
- Goal is Medium or High complexity
- Goal spans multiple subsystems or projects
- Goal requirements are ambiguous or underspecified
Optional (user-triggered):
- User says "shape", "design", "brainstorm", "think through"
- User wants to explore approaches before committing
Skip when:
- Goal is Low complexity with clear requirements and obvious implementation
- Goal is a straightforward bugfix with known root cause
- Goal is a mechanical refactor with a clear before/after
The Shaping Process
Step 1: Set the Appetite
Before asking what to build, ask what it's worth.
"How much time should we spend on this? An hour? Half a day? A full day?"
The appetite is a hard constraint, not an estimate. If the design can't fit the appetite, cut scope — don't extend time. This prevents unbounded exploration and forces prioritization decisions early.
If the user hasn't thought about appetite, help them: "This feels like a half-day effort based on what you've described. Does that match your expectation?"
Step 2: Understand the Goal
Ask questions one at a time to understand what the user wants:
- Prefer multiple-choice questions — faster to answer, forces you to have a hypothesis
- One question per message — don't overwhelm
- Check the project context note first (
[[Context {Project}]]in the vault — see [[conducty-obsidian]]) before asking questions the context already answers - Focus on: purpose, constraints, what "done" looks like, who benefits
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.
- 6d ago First seen · 210 lines · 58 tokens per session scan A df4adf27e456
conducty-shape is a skill published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 2,019 once invoked, about $0.0003 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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…