Borrowing it
Nothing to install: this file belongs to jeeftor/audiobook-organizer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jeeftor/audiobook-organizer/master/.agents/skills/abo-workflow/SKILL.mdgit clone --depth 1 https://github.com/jeeftor/audiobook-organizerWrote 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/jeeftor/audiobook-organizer/abo-workflow)<a href="https://agentmods.dev/skills/jeeftor/audiobook-organizer/abo-workflow"><img src="https://agentmods.dev/badge/skills/jeeftor/audiobook-organizer/abo-workflow/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/jeeftor/audiobook-organizer/abo-workflow"><img src="https://agentmods.dev/badge/skills/jeeftor/audiobook-organizer/abo-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00748 |
| Opus 5.5 | $0.00019 | $0.00299 |
| Sonnet 5.5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
abo-workflow 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 2mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ABO Workflow
You are the Audiobook Organizer workflow coordinator.
Read AGENTS.md and references/abo-assistant/common.md.
Intake
When the user asks to start, pick, or work through repository issues but does not name a specific issue or task, ask whether they want to:
- create a new feature/fix idea, then route through
$abo-issue-create; - choose from the existing GitHub issue list, then route through
$abo-issue-watcher.
If they choose existing issues, inspect open issues first and help pick one before creating a branch or worktree. If they choose new work, capture the goal, motivation, and acceptance criteria before creating the issue and branch.
Closeout Approval Mode
At the start of tracked feature, fix, docs, chore, or test work, ask the user which closeout mode they want for that issue:
- Autonomous closeout: after implementation and verification, the agent may post issue updates, draft PR body files, push the issue branch, open the PR, and enable auto-merge when checks are green.
- Checkpoint closeout: the agent must stop for user approval before posting issue updates, pushing branches, opening PRs, or enabling auto-merge.
- Implementation only: the agent should implement and verify locally, then stop before any GitHub updates or branch pushes.
Record the selected mode in the working notes for the task and carry it into $abo-pr, $abo-pr-create, $abo-pr-watcher, and $abo-issue-closeout. If no mode was selected earlier, ask before the first external closeout action.
This mode does not bypass sandbox, network, or destructive-command approvals. When the selected mode authorizes external closeout actions, use it to make one broad, early approval request where possible instead of interrupting at each routine PR-body, push, issue-comment, or PR creation step.
Route
- New tracked work or branch setup:
$abo-issue-create. - Focused feature implementation:
$abo-feature. - Bug reproduction and fixes:
$abo-bugfix. - Existing issue status, labels, comments, or next steps:
$abo-issue-watcher. - Verify issue acceptance criteria before closeout or PR:
$abo-issue-verify. - Closeout hygiene, changelog/docs/test status, and issue final update:
$abo-issue-closeout. - Test selection, new tests, and verification plans:
$abo-tests. - Audiobookshelf harness or ABS-facing behavior:
$abo-abs-tests. - Current local browser UI work in
web/,internal/server, orinternal/app:$abo-web-ui. - Documentation, AGENTS.md, repo-local skills, or changelog-only work:
$abo-docs. - PR drafting, creation, or watching:
$abo-pr.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 54 lines · 48 tokens per session scan A 2403052730b9
abo-workflow is a skill published in the GitHub repository jeeftor/audiobook-organizer (196 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 748 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ebook-publishing
The complete ebook and audiobook self-publishing skill — write, format, convert, and publish across all major platforms. Use this skill whenever the user asks about Amazon KDP, Apple Books, Gumroad, Payhip, Kobo, Draft2Digital, IngramSpark, Barnes & Noble Press, Google Play Books, PublishDrive, StreetLib, ACX…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
gmeasure
Benchmark and measure Go code with gmeasure — an Experiment groups named Measurements, recorded via RecordValue/RecordDuration/MeasureDuration or repeated Sample/SampleValue/SampleDuration with SamplingConfig, timed inline with a Stopwatch, summarized through GetStats/Stats (StatMin/Max/Mean/Median/StdDev…
octo-mail
OCTO Agent Mail operations for reading, searching, policy-aware sending, preparing drafts, and checking delivery status exclusively through octo-cli.
bex-background-workers
Sets up and configures background workers on bex for queue-based job processing. Use when the user needs to process async jobs, consume from a queue, run Celery/Sidekiq/BullMQ/Asynq/Oban workers, handle graceful shutdown with SIGTERM, wire a worker to Key Value, or choose between workers and cron jobs for background…