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/actionbook/actionbook/outlinegit clone --depth 1 https://github.com/actionbook/actionbookWhat 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 | $0.00000 | $0.00437 |
| Opus 5 | $0.00000 | $0.00218 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
outline 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 3d 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.
What it actually says
/arxiv-viewer:outline
Get the table of contents (outline) of an arXiv paper from ar5iv.org.
Usage
/arxiv-viewer:outline <arxiv_id>
Parameters
arxiv_id(required): arXiv paper ID (e.g.,2301.07041)
Examples
/arxiv-viewer:outline 2301.07041
/arxiv-viewer:outline 1706.03762 # Attention Is All You Need
Workflow
Uses Actionbook + agent-browser to extract structure from ar5iv.org:
search_actions("ar5iv outline")→ get action IDget_action_by_id(action_id)→ get heading selectorsagent-browser open https://ar5iv.org/html/{arxiv_id}agent-browser get text "h2.ltx_title, h3.ltx_title"- Parse and return outline
Output Format
## Paper Outline: {Paper Title}
arXiv: {id}
### Sections
1. Introduction (#S1)
2. Related Work (#S2)
2.1 Background (#S2.SS1)
2.2 Prior Methods (#S2.SS2)
3. Methods (#S3)
3.1 Model Architecture (#S3.SS1)
3.2 Training (#S3.SS2)
4. Experiments (#S4)
5. Results (#S5)
6. Conclusion (#S6)
### Appendices
A. Implementation Details (#A1)
B. Additional Results (#A2)
---
*Use `/arxiv-viewer:read {id} #S3` to read a specific section*
Notes
- Section IDs (like
#S3) can be used with/arxiv-viewer:read - Subsections are indicated by
#S2.SS1format - Appendices typically start with
#A1,#A2, etc.
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.
- 3d ago First seen · 65 lines · 0 tokens per session scan A 2a32b5252965
outline is a command published in the GitHub repository actionbook/actionbook (1,586 stars, last pushed 21d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 437 tokens. 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 commands, from other repositories
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
feedback
File a plugin-capability-gap note, or flush queued notes to GitHub issues.
comms-recall
Search this repo's synced channel messages by keyword and return scored snippets (never the whole history).
daily-standup
../../.github/prompts/daily-standup.prompt.md.
worktree
Set up a git worktree for isolated development.
channels
Guide users through choosing and configuring a channel adapter (WebSocket, Telegram, Discord, Slack, etc.). Use when user asks about channel setup, switching channels, or configuring TALONCHANNEL.