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-handlegit 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 | $0.00059 | $0.00513 |
| Opus 5 | $0.00030 | $0.00257 |
| Sonnet 5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
batch-handle 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.
What it actually says
Task
You will be going on a plan-and-execute spree for non-code work. I will provide a list of tasks or ideas. For each one, write an ops plan and then execute it — without interruptions.
Follow the work-autonomously skill throughout.
Scope check: This workflow produces content, research, specs, and briefs — not code. Never include app codebase changes in plans or execution.
Process
This command composes the two existing batch commands. Run them in sequence using a single shared follow-up file so questions and decisions from both phases land in the same place for review.
1. Planning phase
Follow /ops:batch-plan to produce ordered plan files in plans/ using a shared batch prefix (e.g. music-01-YYYY-MM-DD-<slug>.md, music-02-…, …). Create the follow-up file at the start of this phase — reuse it for the execution phase instead of creating a second one.
Skip /ops:batch-plan's own review step: do NOT run /review-followup between phases, and do NOT delete the follow-up file. The user reviews everything once at the end.
2. Execution phase
Follow /ops:batch-execute against the plans just written, passing the same follow-up file. Execute plans in the order their prefixes indicate.
Skip /ops:batch-execute's final /review-followup step as well — you'll run it once at the very end.
3. Review
Once all plans are executed, run /review-followup on the shared follow-up file. After all items are resolved, confirm with the user to merge the branch back into the main branch, then perform the merge.
Why compose instead of duplicate
/ops:batch-plan and /ops:batch-execute already encode the details of each phase (planner/executor sub-agents, commit discipline, insight persistence, follow-up conventions). This command exists only to chain them with a shared follow-up file and a single review at the end — don't restate their instructions here.
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 · 37 lines · 59 tokens per session scan A 9f5d99346244
batch-handle is a command published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 14d ago), licensed MIT. It adds 59 tokens to every session and 513 once invoked, about $0.0003 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.