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/whats-nextgit clone --depth 1 https://github.com/OdinMB/ops-workflowWrote 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/odinmb/ops-workflow/whats-next)<a href="https://agentmods.dev/commands/odinmb/ops-workflow/whats-next"><img src="https://agentmods.dev/badge/commands/odinmb/ops-workflow/whats-next.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.01308 |
| Opus 5 | $0.00016 | $0.00654 |
| Sonnet 5 | $0.00006 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
whats-next 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 4d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate an executive overview for this project. $ARGUMENTS
Instructions
1. Gather Context
Read only the high-level INDEX files first. Be selective about drilling into details — only read individual files when needed to answer a specific question or fill a gap.
Round 1 — INDEX files only (skip any that don't exist):
MEMORY.md— Project overview and knowledge map.state/INDEX.md— Area names and status summaries.backlog/INDEX.md— Priorities and item titles.plans/INDEX.md— Note active vs completed plans.
Round 2 — Selective drill-down:
- Read active plan files (not completed ones — titles in the INDEX are enough for momentum context).
- Read up to 3 individual state or backlog files if they're directly relevant to your recommendations or the user's focus area. No more than 3.
2. Analyze
With all context loaded, assess:
- Momentum: What has been accomplished recently? What's the trajectory?
- Bottlenecks: What's blocking progress? Are there unresolved decisions, missing prerequisites, or resource constraints?
- Quick wins: What high-impact items can be done with minimal effort?
- Strategic bets: What bigger moves could shift the project's trajectory?
- Staleness: Are any state files outdated? Are backlog items obsolete?
3. Output
Present the overview using this structure. Do not explain the project — the user knows what it is. Focus on where things stand and what to do next.
Header
# Executive Overview
_Generated: <today's date>_
Status Dashboard
A compact table showing key metrics at a glance. Pull numbers from state files. Use — for unknown values.
Derive areas from top-level state entries (folders and files directly under state/). Each row corresponds to one top-level entry. Do NOT nest every sub-topic — only add └ child rows for sub-areas where something particularly noteworthy is happening right now (e.g., a recent launch, an upcoming deadline, a specific blocker). Most state areas should be a single row. Keep the dashboard to 3-5 top-level rows with 0-2 nested rows total.
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.
- 4d ago First seen · 139 lines · 32 tokens per session scan A 65e6e1aa7881
whats-next is a command published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 17d ago), licensed MIT. It adds 32 tokens to every session and 1,308 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
close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
entry
Load a Linear issue into context and enter plan mode for a focused session.
submit
Move the current branch's Linear issue to In Review.
setup-linear
Configure .factory-kit/linear.json for the portable Linear workflows.
standup
Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog.
backlog
PitWay: Capture out-of-scope work discovered mid-task, without expanding current scope.