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 work-autonomouslygit 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/work-autonomously)<a href="https://agentmods.dev/skills/odinmb/ops-workflow/work-autonomously"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/work-autonomously/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/work-autonomously"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/work-autonomously.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 | $0.00030 | $0.01703 |
| Opus 5.5 | $0.00012 | $0.00681 |
| Sonnet 5.5 | $0.00006 | $0.00341 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
work-autonomously 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Conventions
Rules for commands and skills that run without user input (e.g., /ops:get-to-work, /ops:batch-execute). The goal is to keep moving and defer human judgment to a structured follow-up review.
Core Rules
- Never stop for user input. Record questions and move on.
- Delete only what the list below allows. Record every other intended deletion under Files to Delete in the follow-up file.
- Never push to remote. Only local branches and commits.
- Commit with explicit pathspecs. Name the paths you changed on the commit itself:
git add -- <path> <path> …(needed for new files, which a commit pathspec alone does not pick up), thengit commit -m "<message>" -- <path> <path> …. Nevergit add -A,git add .orgit commit -a, and never a baregit commitafter staging: a plain commit takes the whole index, so it can sweep a parallel agent's or the user's half-finished work into your commit. Work out the paths from the agent's summary andgit status. - When uncertain, make a sensible choice and move on. Record your reasoning and alternatives in the follow-up file so the user can review. Only skip when the wrong choice could have truly bad consequences (data loss, security, breaking external contracts). Getting work done with transparent doubts beats a slightly lower chance of mistakes.
- No real-world actions (the list below).
- Goals and autopilot's files are the user's. Never change
charter.md: a goal, audience or non-goal that looks wrong goes under User Input Needed. Where the repo's CLAUDE.md has an## Autopilotsection, never edit, move or deletestate/autopilot.mdorreferences/autopilot-policy.mdeither: they are autopilot's alone. Every other file is shared, and a run works in it by the usual rules.
Real-world actions an unattended run never takes
This is the one full list; agents and commands point here. Never:
- Send emails, messages, or notifications
- Submit forms, applications, or registrations
- Post to social media or external platforms
- Make API calls that modify external state
- Make purchases or financial transactions
- Contact anyone on behalf of the user
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 a50ababcf7fb
- yesterday Changed · +7 lines 06232ffe87f1
- 2d ago Changed · +15 lines dff49218c653
- 23d ago Changed · +13 lines cacf81e2b705
- 1mo ago First seen · 64 lines · 30 tokens per session scan A d97de5bc9f08
work-autonomously is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,703 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…