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/unwind_openai)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/unwind_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/unwind_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/unwind_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/unwind_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 | $0.00012 | $0.01660 |
| Opus 5.5 | $0.00005 | $0.00664 |
| Sonnet 5.5 | $0.00002 | $0.00332 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade A, and why
unwind_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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<workflow_contract>
- Follow all 6 steps in order.
- Prefer explicit state over vague narrative.
- Distinguish confirmed facts, settled decisions, and tentative/open items.
- If you can identify the current workflow command, record it explicitly and re-read that command file before writing the artifact.
- The artifact must be sufficient for a fresh session that knows only the repo, system prompts, and this artifact.
- Validation claims must be labeled
confirmed,inferred, orunconfirmed. - If workflow prompt files or
opencode.jsonchanged in this session, record whether a post-write comparison pass already happened or is still required. - If uncertainty remains, label it explicitly instead of smoothing it over. </workflow_contract>
<step_1>
Step 1: Identify Scope and Workflow
- Infer the current task and handoff scope from the active session plus
<userMessage>. - Treat additional user text as handoff focus, resume emphasis, or overrides.
- Determine whether the current work is primarily associated with a known workflow command such as:
.opencode/command/implement_plan.md.opencode/command/research.md.opencode/command/create_plan_init.md.opencode/command/create_plan_final.md.opencode/command/review_pr_comments.md
- If a known workflow is identified, record:
source_workflow_command= slash-command form such as/implement_plansource_workflow_file= repo path such as.opencode/command/implement_plan.mdresume_mode= one ofcontinue_source_workflow,continue_generic_work, orask_user_first
- If the workflow is unclear, fall back to a generic handoff and say so explicitly in the artifact.
</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 · 164 lines · 12 tokens per session scan A c70663474fa3
unwind_openai is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 1,660 once invoked, about $0.0000 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.