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/helpgit clone --depth 1 https://github.com/athrael-soju/framework-generatorWhat 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 | $0.00006 | $0.00357 |
| Opus 5 | $0.00003 | $0.00179 |
| Sonnet 5 | $0.00001 | $0.00071 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
help 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.
What it actually says
Framework Generator Help
The Framework Generator creates structured, repeatable frameworks with executable skills through staged refinement.
Commands
| Command | Description |
|---|---|
/framework-generator:frame |
Define framework purpose and boundaries |
/framework-generator:organize |
Map stages and flow |
/framework-generator:refine |
Specify each stage in detail |
/framework-generator:generate |
Produce framework plugin with command files |
/framework-generator:evaluate |
Validate and iterate |
Workflow
Frame → Organize → Refine → Generate → Evaluate
↑__________________________________________|
(feedback loops)
Quick Start
-
Start a new framework:
/framework-generator:frame my-framework -
Continue through stages:
- Each stage produces artifacts in
output/{date}/{name}/ - Approve each stage before proceeding to the next
- Use feedback loops to return to earlier stages if needed
- Each stage produces artifacts in
Stage Outputs
| Stage | Output Location |
|---|---|
| Frame | 1-frame/charter.md |
| Organize | 2-organize/stage-map.md |
| Refine | 3-refine/{stage}-spec.md |
| Generate | 4-generate/{framework-name}/ (full framework) |
| Evaluate | 5-evaluate/validation.md |
Principles
- Human approval gates at every stage handoff
- Quality criteria checklists for each stage
- Feedback loops for iteration
- Self-contained command files (no external references)
More Information
See the plugin README for detailed documentation.
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 · 59 lines · 6 tokens per session scan A e42abffc7bd0
help is a command published in the GitHub repository athrael-soju/framework-generator (2 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 357 once invoked, about $0.0000 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 2026-08-31.
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.