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/resume_work_openai)<a href="https://agentmods.dev/commands/allisoneer/agentic_auxilary/resume_work_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/resume_work_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/resume_work_openai"><img src="https://agentmods.dev/badge/commands/allisoneer/agentic_auxilary/resume_work_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 | $0.00010 | $0.01456 |
| Opus 5.5 | $0.00004 | $0.00582 |
| Sonnet 5.5 | $0.00002 | $0.00291 |
| Haiku 4.5 | $0.00001 | $0.00146 |
Grade A, and why
resume_work_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 — 144 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.
- Read the handoff artifact fully before any other major action.
- Re-read the source workflow command file if the artifact names one.
- Treat the artifact as canonical unless current repository files contradict it.
- Create
todowriteimmediately after reconstructing state. - Do not redo completed work unless the artifact or current files show contradiction or drift.
- If the artifact contains unresolved blockers that require the user, stop and ask instead of guessing.
- Treat
confirmed,inferred, andunconfirmedvalidation claims differently; onlyconfirmedmeans verified work. - If you create or edit workflow prompt files (for example
.opencode/**) oropencode.json, do a post-write comparison pass before treating that work as complete. </workflow_contract>
<step_1>
Step 1: Load the Handoff Artifact
- Parse the handoff artifact path from
<userMessage>. - Treat any remaining text in
<userMessage>as this session's override instructions. - Read the handoff artifact fully before doing anything else.
- Extract at least these values from the artifact:
source_workflow_commandsource_workflow_fileresume_moderecommended_resume_commandif present- anchor documents from
## Resume Protocol - first actions
- do not redo list
- remaining work
- validation status
- If no valid handoff artifact path is available, ask the user for it and stop.
- If the artifact is missing important sections, state what is missing and continue only if the remaining information is still usable.
</step_1>
<step_2>
Step 2: Reconstruct Instructions and Context Separately
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 · 144 lines · 10 tokens per session scan A cd2c4c058ebb
resume_work_openai is a command published in the GitHub repository allisoneer/agentic_auxilary (79 stars, last pushed 6d ago), licensed MIT. It adds 10 tokens to every session and 1,456 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
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.