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/athrael-soju/framework-generator/generategit clone --depth 1 https://github.com/athrael-soju/framework-generatorWrote 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/commands/athrael-soju/framework-generator/generate)<a href="https://agentmods.dev/commands/athrael-soju/framework-generator/generate"><img src="https://agentmods.dev/badge/commands/athrael-soju/framework-generator/generate.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 | $0.00010 | $0.01460 |
| Opus 5 | $0.00005 | $0.00730 |
| Sonnet 5 | $0.00002 | $0.00292 |
| Haiku 4.5 | $0.00001 | $0.00146 |
Grade B, and why
generate scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**5. Generate Settings** - Create `4-generate/{framework-name}/.claude/settings.local.json`: How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate
Produce a framework plugin with command files.
Inputs
| Input | Source |
|---|---|
| framework_charter | Frame stage output |
| stage_map | Organize stage output |
| stage_specifications | Refine stage output |
Input Format
From Frame stage (output/{date}/{name}/1-frame/charter.md):
# Framework Charter: {NAME}
## Problem
## Purpose
## Scope
## Type
## Dependencies
From Organize stage (output/{date}/{name}/2-organize/stage-map.md):
# Stage Map: {NAME}
## Stages
| Stage | Purpose | Inputs | Outputs |
## Flow
{Mermaid diagram}
## Feedback Loops
## Terminal States
From Refine stage (output/{date}/{name}/3-refine/{stage}-spec.md):
# Stage Specification: {STAGE}
## Purpose
## Activities
## {Context Tables}
## Output Format
## Quality Criteria
## Completion
Process
1. Generate Plugin Manifest - Create 4-generate/{framework-name}/.claude-plugin/plugin.json:
- Plugin name from framework name
- Version 1.0.0
- Description from charter purpose
2. Generate README - Create 4-generate/{framework-name}/README.md:
- Framework overview from charter
- Commands table with descriptions
- Quick start guide
- Output structure specific to this framework
3. Generate Command Files - For each stage:
- Create directory:
4-generate/{framework-name}/commands/ - Create command file:
4-generate/{framework-name}/commands/{stage}.md - Include: frontmatter (description, argument-hint), inputs table, input format, process steps, output with embedded templates, quality criteria, completion
- Commands should be self-contained (no references to external docs)
4. Generate CLAUDE.md - Create 4-generate/{framework-name}/CLAUDE.md:
- AI assistant instructions for this framework
- Document index (README, commands/)
- Interaction protocol: explicitly instruct use of
AskUserQuestiontool for gathering input, clarification, and approval requests
5. Generate Settings - Create 4-generate/{framework-name}/.claude/settings.local.json:
- Copy permission settings for Claude Code
- Enables streamlined execution without repeated permission prompts
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.
- 3d ago First seen · 244 lines · 10 tokens per session scan B 8b8c6ffc2b8d
generate is a command published in the GitHub repository athrael-soju/framework-generator (2 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,460 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
log-time
Log work hours on an Atera ticket.
run-powershell
Execute a PowerShell script on an Atera agent.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
update-ticket
Update fields on an existing Atera ticket.
alert-triage
Triage open Auvik alerts, rank by severity, and recommend dismissals for known noise.
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.