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 skills add OdinMB/ops-workflow --skill prioritizegit 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/skills/odinmb/ops-workflow/prioritize)<a href="https://agentmods.dev/skills/odinmb/ops-workflow/prioritize"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/prioritize/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/skills/odinmb/ops-workflow/prioritize"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/prioritize.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 | $0.00035 | $0.00961 |
| Opus 5.5 | $0.00014 | $0.00384 |
| Sonnet 5.5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
prioritize 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 today.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ops Prioritize
Given a project's active plans, backlog, and goals, select the tasks genuinely worth executing now — at most 3. The output is a ranked shortlist with execution order — this skill does NOT execute them.
Context Required
You need the full project overview loaded (charter.md, MEMORY.md, state, backlog, active plans) plus any newly identified work items from find-tasks.
The project's goals are in charter.md (a repo set up before it existed keeps them in MEMORY.md): weigh impact against them.
Selection Criteria
Score each candidate task on these dimensions:
Impact (weight: high)
How much does completing this task move the project toward its goals?
- High: directly advances a primary goal, unblocks other work, or fills a critical knowledge gap
- Medium: advances a secondary goal, improves project quality, or creates useful reference material
- Low: nice-to-have, minor cleanup, or distant from current priorities
Feasibility (weight: high)
Can an autonomous agent complete this task without human input or real-world actions?
- High: pure research, writing, analysis, or knowledge management — all inputs are available
- Medium: mostly feasible, but may need assumptions about preferences or priorities
- Low: requires external information the agent can't access, real-world actions, or significant subjective judgment
Tasks with low feasibility should be skipped — they'll end up in the follow-up file anyway.
Independence (only for tasks meant to run in parallel)
Tasks that will run one after another need not be independent. If the caller wants to run two in parallel, they must be:
- Tasks that modify the same files are NOT independent
- Tasks where one's output is the other's input are NOT independent
- Tasks touching different backlog areas, state files, or reference topics are usually independent
Process
Step 1: Inventory
List all candidate tasks from:
- Active plans in
plans/— these are already approved work, except an autopilot cycle record (*autopilot-cycle*), which is autopilot's record, not a plan - Backlog items — particularly those marked as high priority or quick wins; where the repo's CLAUDE.md has an
## Autopilotsection, notbacklog/ideas.mdor an item marked(code item), which are autopilot's to route or build - Newly identified items from the latest
find-tasksrun
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.
- today Changed 98141d0da22a
- yesterday Changed · +2 lines 0140b68100c3
- 2d ago Changed · -18 lines · +6 tokens per session 3c98ef004a40
- 1mo ago First seen · 116 lines · 29 tokens per session scan A d561e7f5417c
prioritize is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 961 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…
factory-design
Design-system discipline distilled across builds. Semantic token vocabulary (name intent, not palette position), CSS variables bridged into Tailwind, dark/light as a variable swap, single- vs two-layer token systems, component primitives as token consumers, when to promote a repeated utility cluster into a primitive…
factory-frontend
Frontend conventions distilled across builds. CRUD shape (DataTable + drawer with mode union), RowActions primitive, format helpers, heading tiers, semantic color tokens, query-key naming, component-library decision criteria (Mantine vs shadcn). Read when scaffolding any UI surface that touches lists, forms, or entity…
factory-auth
Auth and authorization conventions distilled across builds with three different auth stacks (Better Auth + orgs, Supabase Auth + RLS, Clerk). Covers the provider decision matrix, the unified wrapper interface (requireAuth / requireRole / withOrgContext), procedure tier stacking, session handling, OAuth callback…