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 commands/jeffh/claude-plugins/import-humanlayergit clone --depth 1 https://github.com/jeffh/claude-pluginsWhat 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 | $0.00011 | $0.00867 |
| Opus 5 | $0.00005 | $0.00434 |
| Sonnet 5 | $0.00002 | $0.00173 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
import-humanlayer 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Import HumanLayer Commands and Agents
You are tasked with importing humanlayer commands and agents from a source repository and adapting them for use in this repository.
Input
The user will provide a path to the humanlayer repository as an argument to this command.
Process
Step 1: Validate Input Path
- Check that the provided path exists and is a directory
- Verify that the path contains
.claude/commands/and.claude/agents/directories - If validation fails, report the error and stop
Step 2: Copy Files
- Copy all files from
<humanlayer_repo>/.claude/commands/tohumanlayer/commands/ - Copy all files from
<humanlayer_repo>/.claude/agents/tohumanlayer/agents/ - Use
cp -rto preserve file attributes - Report which files were copied
Step 3: Remove Syncing Functionality
For each copied file (both commands and agents):
- Read the file content
- Remove all references to syncing functionality:
- Remove any usage of
thoughts synccommands - Remove any sync-related instructions or steps
- Remove any references to syncing thoughts directory
- Remove any sync verification steps
- Remove any usage of
- If a file is modified, write the updated content back
- Report which files were modified and what was removed
Step 4: Convert Script References to Skills
For each copied file (both commands and agents):
- Search for references to scripts in
scripts/*andhack/*directory - For each script reference found:
- Read the script content from the source repository
- Create a new skill directory in
humanlayer/skills/with a descriptive name based on the script's purpose - Create a
SKILL.mdfile inside the skill directory with proper frontmatter:--- name: script-name description: What this skill does and when Claude should activate it allowed-tools: Bash, Read --- - Convert the script's functionality into skill instructions within
SKILL.md - Replace the script reference in the original file with instructions to use the Skill tool
- Report which skills were created and which script references were replaced
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 · 103 lines · 11 tokens per session scan A fa7bd50f5a5d
import-humanlayer is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 11 tokens to every session and 867 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.