HumanLayer is a software system that runs coding agents on a team’s machines and coordinates their tasks, sessions, plans, and reviews through desktop and web apps. Its Turborepo monorepo contains the user interfaces, host daemon, API, command-line tools, synchronization services, and agent plugins. The catalogue entries provide skills, plugins, instructions, and settings for its coding-agent workflows.
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 humanlayer/humanlayer --skill iterate-structure-outlinegit clone --depth 1 https://github.com/humanlayer/humanlayerWrote 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/humanlayer/humanlayer/iterate-structure-outline)<a href="https://agentmods.dev/skills/humanlayer/humanlayer/iterate-structure-outline"><img src="https://agentmods.dev/badge/skills/humanlayer/humanlayer/iterate-structure-outline/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/humanlayer/humanlayer/iterate-structure-outline"><img src="https://agentmods.dev/badge/skills/humanlayer/humanlayer/iterate-structure-outline.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 | $0.00017 | $0.01520 |
| Opus 5.5 | $0.00007 | $0.00608 |
| Sonnet 5.5 | $0.00003 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
iterate-structure-outline 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 2d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterate Structure Outline
You are iterating on an existing structure outline document based on user feedback.
Input
- If only a directory is provided, or a directory is not provided, check the task's artifact directory from your prompt:
ls -La .humanlayer/tasks/<task slug>. Do NOT use grep or glob orlsorls -l, as the directory may be a symlink. - Optionally, a ticket file path containing comments with feedback
Initial Check
If the user calls this with no instructions or feedback, ask them for their feedback:
I'm ready to iterate on the structure outline. What feedback or changes would you like me to incorporate? For example:
- Phase reorganization
- Scope changes (add/remove items)
- Answers to open questions
- Additional context or requirements
Then wait for the user's feedback before proceeding.
Steps
-
Read all input documents FULLY:
- Use Read tool WITHOUT limit/offset to read the structure outline and all prior artifacts (
ticket.mdortask.md, research, design discussion, PRD/TDD if present) - Understand the current state of the codebase from research findings
- Review all design decisions and patterns to follow
- Use Read tool WITHOUT limit/offset to read the structure outline and all prior artifacts (
-
Check for related task content:
- If a path in
.humanlayer/tasks/TASKNAMEis mentioned, usels -La .humanlayer/tasks/TASKNAME. Do NOT uselsorls -las the directory may be a symlink. - Read all relevant files in the task directory, including the structure outline, design discussion, research documents, and ticket
- Read relevant files mentioned in the task files
- If a path in
-
If the user gives any input:
- DO NOT just accept the correction blindly
- Spawn research tasks to verify the information if needed
- Read the specific files/directories they mention
- Only proceed once you've verified the facts yourself
-
Spawn sub-agents for follow-up research (if needed):
For deeper investigation:
- codebase-locator: Find additional files if needed
- codebase-analyzer: Deep-dive on specific implementations
- codebase-pattern-finder: Find more examples of patterns
- web-search-researcher: Research external best practices
- You may see a humanlayer library researcher tool. If you do, you should use this to answer any research questions about dependencies and libraries. If the tool is not present, do not mention it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 154 lines · 17 tokens per session scan A f2d996fef376
iterate-structure-outline is a skill published in the GitHub repository humanlayer/humanlayer (12,428 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 1,520 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 2026-10-23.
Other skills, from other repositories
feature-handoff
Emit the complete feature handoff with exact modes, outcomes, CUJs, demos, and publication state.
feature-requirements
Turn the ticket into requirements and CUJs, and stop with a split proposal when it is too big.
jira-release
Assemble a release from a batch of Jira issues — one release branch, pull request, preview and tracking issue per repository — and, when a person says to ship it, merge it and move the cards on. Insert into the prompt of a run started on a batch of issues.
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
cococonverge
CocoPivot — multi-pod convergence synthesizer. Deterministically deduplicates findings from N parallel pod outputs into one prioritized, coordinated action plan. Invoked via $pivot run/show/status/clear.