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/allisoneer/agentic_auxilaryWrote 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/allisoneer/agentic_auxilary/frame_openai)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/frame_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/frame_openai/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/commands/allisoneer/agentic_auxilary/frame_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/frame_openai.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 | $0.00018 | $0.01678 |
| Opus 5.5 | $0.00007 | $0.00671 |
| Sonnet 5.5 | $0.00004 | $0.00336 |
| Haiku 4.5 | $0.00002 | $0.00168 |
Grade A, and why
frame_openai 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 1mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
For this command, the requested work is the framing itself. Producing a grounded frame and either routing cleanly or proceeding with bounded work counts as completion.
<workflow_contract>
- Follow all 6 steps in order.
- Treat the user prompt as meaningful even if it is short.
- Distinguish clearly between confirmed facts, inferred framing, and open questions.
- Continue tool use until the frame is grounded enough to route or act responsibly; for this command, that grounded frame is the completion target unless direct execution mode is chosen.
- Prefer
tools_ask_agentfor grounded discovery when codebase facts matter. - If a specialized workflow command is clearly the better fit, recommend it explicitly instead of forcing direct execution.
- If the request is bounded enough to answer or execute directly after framing, proceed directly.
- Ask a clarification question only when the prompt lacks enough subject matter to frame responsibly. </workflow_contract>
<step_1>
Step 1: Parse the Prompt and Classify It
- Read
<userMessage>carefully and infer the most likely explicit request. - Infer the likely deeper objective behind the wording when one is apparent.
- Classify the prompt across these axes:
- task type: question | research | planning | implementation | review | resume | handoff | mixed
- scope: single file | subsystem | cross-cutting | repo-wide | unknown
- ambiguity: fully unclear | partially specified | mostly clear
- If the prompt names files, documents, commands, PRs, or plans, record them as anchor points.
- If the prompt has too little subject matter to frame responsibly, ask one clarification question and stop.
</step_1>
<step_2>
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.
- 1mo ago First seen · 172 lines · 18 tokens per session scan A 139b9a0315b3
frame_openai is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 1,678 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 2026-09-08.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
r
Resume the last handoff and carry on with the outstanding work.
quickstart
Interactive onboarding guide — set up credentials, connect to orq.ai, and learn every command and skill.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.