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-plangit 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 | $0.00042 | $0.00843 |
| Opus 5 | $0.00021 | $0.00421 |
| Sonnet 5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
batch-plan 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 — 66 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 writing spree for non-code work. I will provide a list of tasks or ideas. Write an ops plan for each of these items without interruptions.
Follow the work-autonomously skill throughout.
Guidelines
- Create a follow-up file per the
work-autonomouslyskill. - At the start of the batch, pick a short slug-style batch prefix that names the theme of this batch (e.g.
music,q2-launch,donor-outreach). Use the user's framing if they offered one; otherwise derive it from the tasks. Keep it lowercase, hyphenated, and brief. - Filenames of plans should reference the goal of the plan, with today's date and the batch+order prefix:
<batch>-<NN>-YYYY-MM-DD-<slug>.md(e.g.music-01-2026-04-19-launch-brief.md). The batch prefix keeps multiple concurrent ordered batches inplans/from stepping on each other. - You can write plans in parallel if they don't directly relate to each other.
- Scope check: Plans must never include implementing changes in app codebases. This workflow produces content, research, specs, and briefs — not code.
Triage
Before planning, classify each task as trivial or needs-plan:
- Trivial — a single obvious deliverable with no open questions: a small content edit, a one-paragraph note, updating a single field in a tracker, pasting known information into a document, a short email draft. No research required, no structural decisions, no stakeholder calls to resolve.
- Needs-plan — everything else: multi-step work, research, content requiring judgment, anything with open questions a planner could usefully surface.
When in doubt, treat it as needs-plan.
Trivial tasks skip the planner entirely and go into a single plans/<batch>-direct-tasks.md file as numbered entries. Non-trivial tasks get planned as usual. Use the same numeric prefix sequence for both so execution order across the whole batch is preserved. With batch prefix music:
- Task 1 (trivial) → entry
01.inplans/music-direct-tasks.md - Task 2 (needs-plan) →
plans/music-02-YYYY-MM-DD-<slug>.md - Task 3 (trivial) → entry
03.inplans/music-direct-tasks.md - Task 4 (needs-plan) →
plans/music-04-YYYY-MM-DD-<slug>.md
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 · 66 lines · 42 tokens per session scan A 44afc6feecdb
batch-plan is a command published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 14d ago), licensed MIT. It adds 42 tokens to every session and 843 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.