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/odinmb/ops-workflow/batch-executegit clone --depth 1 https://github.com/OdinMB/ops-workflowWhat 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 | $0.00044 | $0.00783 |
| Opus 5 | $0.00022 | $0.00392 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
batch-execute 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 yesterday.
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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
You will be going on a plan execution spree for non-code work. I will provide a list of plans. Execute these plans one by one without interruptions.
Follow the work-autonomously skill throughout.
Steps
- Check the current branch — if you're already on a feature branch, stay on it. Only create a new branch if you're on
main(or the repo's default branch). - Identify the batch prefix to process. The user usually names it (e.g. "execute the music batch"); otherwise infer it from the plan files they list, or ask. Plans use the convention
plans/<batch>-NN-YYYY-MM-DD-<slug>.mdandplans/<batch>-direct-tasks.mdso multiple concurrent batches can coexist inplans/. - Create a follow-up file per the
work-autonomouslyskill. - Build the ordered work queue: merge plan files (
plans/<batch>-NN-*.md) and any entries inplans/<batch>-direct-tasks.mdinto a single list sorted by numeric prefix. Only include files matching this batch's prefix — leave other batches alone. Don't look ahead, don't run items in parallel. - Process the queue in order. Plan-file items go through the plan-based flow below; direct-task items go through the direct-task flow.
- After all items are processed, use the
/review-followupskill to walk through follow-up items with the user. - When all follow-up items are resolved, confirm with the user to merge the branch. Then perform the merge.
Execution (plan files)
For each plan file, spawn an executor sub-agent (agents/executor.md):
Read the executor agent instructions at: agents/executor.md
Plan file path: <path to the plan>
Follow-up file path: <path to the follow-up file>
After each executor agent completes:
- Review its summary for status and any follow-up items. Note the summary's Effort line — if one delegation's effort dwarfs its peers, mention it in the follow-up file so the batch's expensive spots stay visible.
- Verify the agent persisted insights: check if MEMORY.md or backlog files were updated when appropriate. If the agent produced findings but didn't persist them, do it now.
- Commit all changes (artifacts + state updates + completed plan) with a descriptive message
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.
- yesterday First seen · 55 lines · 44 tokens per session scan A 12f840786c58
batch-execute is a command published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 14d ago), licensed MIT. It adds 44 tokens to every session and 783 once invoked, about $0.0002 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
kb-ingest
Esegui un ingest nella LLM Wiki per il progetto o argomento specificato: $ARGUMENTS.
kb-output
Esporta una pagina della LLM Wiki in formato slide deck Marp: $ARGUMENTS.
kb-promote
Promuovi il concetto specificato da llm-wiki/wiki/concepts/ alla KB stabile (questo repo o un fork): $ARGUMENTS.
kb-lint
Esegui un controllo qualità completo della LLM Wiki in $LLMWIKIPATH.
close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
prompt
Convert a rough ask into a structured XML-tagged prompt using the factory-prompting vocabulary.