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-improvegit 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-improve)<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-improve"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-improve/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.
<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-improve"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.01339 |
| Opus 5 | $0.00034 | $0.00669 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
conducty-improve 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 9d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conducty Improve — The Learning Loop
The improvement kata transforms execution data into process improvements. Without this step, Conducty is an execution pipeline that repeats the same mistakes. With it, Conducty is a learning system that gets better with every plan.
This is the step that closes the feedback loop: Shape → Plan → Execute → Verify → Improve → Shape (next plan).
The Improvement Kata
Adapted from Toyota Kata (Mike Rother) — four questions applied to agentic work.
Question 1: What Was the Target Condition?
Read the just-finished plan note from the vault (Plans/Plan YYYY-MM-DD HHmm [Topic].md — see [[conducty-obsidian]]):
- What goals were set?
- What was the appetite?
- What was the expected pass rate and velocity?
- What improvement experiments from the prior plan were being tested?
Question 2: What Is the Current Condition?
Read the plan's review results (the ## End-of-Plan Summary and ## Checkpoint Notes):
- What actually happened? How many prompts completed vs. failed?
- What was the first-attempt pass rate?
- How did actual time compare to appetite?
- Did the improvement experiments from the prior plan show results?
Question 3: What Obstacles Did We Encounter?
Read recent entries from [[Failure Patterns]] (the accumulating note in the vault):
- What patterns caused failures?
- At which leverage level were most failures? (plan / prompt / code)
- Which prompt smells were most common?
- Were there systemic issues?
- What surprised us?
Categorize obstacles:
| Category | Example | Fix Level |
|---|---|---|
| Stale context | Agent used outdated architecture info | Refresh [[conducty-context]] |
| Prompt smell | Vague acceptance criteria led to wrong implementation | Improve prompt template |
| Design gap | Shaping missed a key constraint | Improve [[conducty-shape]] process |
| Calibration error | Low complexity prompt turned out to be Medium | Adjust complexity estimation |
| Template weakness | Bug fix template didn't include characterization step | Fix the template |
| Tool limitation | Agent model couldn't handle the task complexity | Adjust model selection |
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.
- 9d ago First seen · 133 lines · 69 tokens per session scan A 59b60e3f849c
conducty-improve is a skill published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,339 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.