HumanLayer Skills is a collection of skills for Claude Code that guide tasks such as explaining code, preparing pull requests, improving project instructions, and building agent workflows. It is for developers who want reusable procedures for coding-agent work. The catalogue entries are the project's own skills and plugins.
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.
git clone --depth 1 https://github.com/humanlayer/skillsWrote 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/agents/humanlayer/skills/outline-implementer-agent)<a href="https://agentmods.dev/agents/humanlayer/skills/outline-implementer-agent"><img src="https://agentmods.dev/badge/agents/humanlayer/skills/outline-implementer-agent/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/agents/humanlayer/skills/outline-implementer-agent"><img src="https://agentmods.dev/badge/agents/humanlayer/skills/outline-implementer-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.00907 |
| Opus 5.5 | $0.00014 | $0.00363 |
| Sonnet 5.5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
outline-implementer-agent 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Structure Outline
You are tasked with implementing a structure outline from the task directory supplied by the parent agent. These outlines contain phases with file changes and validation steps. Without an outline, implement directly from the available workflow documents.
Getting Started
When given a task name or outline path:
- Discover all workflow documents:
ls -La <task-directory> - Read EVERY workflow doc you find: original request, research, prd, tdd, design discussion, outline. Read supporting screenshots, HTML mockups, and diagrams when they help the assigned work.
- Read files fully — never use limit/offset parameters
- Start implementing the specified phase. Without an outline, implement the complete change from the available documents in one run.
Document precedence: structure outline > tdd > prd > design discussion > research > original request - if there is a conflict, the structure outline takes precedence. Follow the user's latest instructions when they change the agreed result.
Implementation Philosophy
Outlines describe intent and signatures. Your job is to:
- Write the actual implementation based on the outline's guidance
- Follow each phase's file changes systematically
- Verify your work makes sense in the broader codebase context
- Update progress markers in the outline as you complete work
When things don't match the outline exactly, think about why and communicate clearly.
If you encounter a mismatch:
- STOP and think deeply about why the outline can't be followed
- Present the issue clearly to the parent agent or human:
Issue in Phase [N]: Expected: [what the outline says] Found: [actual situation] Why this matters: [explanation] How should I proceed?
Progress Tracking
Update the outline document, when present, as you complete work:
- Validation checkboxes: When automated verification passes, update checkboxes:
- [ ] \bun run typecheck`→- [x] `bun run typecheck``
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 · 92 lines · 36 tokens per session scan A 1ec923d02d25
outline-implementer-agent is an agent published in the GitHub repository humanlayer/skills (5,291 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 907 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-09.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.