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 markoblogo/abvx-agent-skills --skill rabbithole-doc-explorationgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/rabbithole-doc-exploration)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/rabbithole-doc-exploration"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/rabbithole-doc-exploration/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/markoblogo/abvx-agent-skills/rabbithole-doc-exploration"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/rabbithole-doc-exploration.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 | $0.00069 | $0.00618 |
| Opus 5 | $0.00034 | $0.00309 |
| Sonnet 5 | $0.00014 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
rabbithole-doc-exploration 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rabbithole Doc Exploration
Use a local Rabbithole MCP canvas to inspect dense documents with the human before turning findings into durable repo changes.
Use When
- reviewing
AGENTS.md,RUNBOOK.md,docs/ai/repomap.compact.md, or generated repo contracts; - reviewing
SKILL.mdfiles, skill cards, or workflow packs; - reviewing SET planner exports such as
orchestrator-bundle.jsonorrabbithole.seed.md; - the user wants to branch into questions from selected text instead of reading a long document linearly.
Inputs
Good starting documents:
docs/ai/rabbithole.seed.mdAGENTS.mdRUNBOOK.mddocs/ai/repomap.compact.md.set-plan/orchestrator-bundle.json.set-plan/rabbithole.seed.mdskills/<name>/SKILL.md
Workflow
- Check availability
- If Rabbithole MCP tools are available, use
open_rabbitholewith a title and file path or content. - If they are not available, continue as a normal document review and tell the user Rabbithole is optional.
- If Rabbithole MCP tools are available, use
- Open the smallest useful seed
- Prefer
docs/ai/rabbithole.seed.mdor.set-plan/rabbithole.seed.mdwhen present. - Otherwise open the single document the user named.
- Prefer
- Answer branches
- Treat each selected passage as the anchor.
- Answer with concrete file paths, risks, and proposed doc/code follow-ups.
- Keep answers branch-sized; do not turn every branch into a full audit.
- Promote findings carefully
- Only write durable repo docs when the finding is stable and broadly useful.
- Keep Rabbithole notes out of CI contracts unless the repo explicitly stores them.
- Close with a compact synthesis
- List decisions, doc changes made, open questions, and any branch findings that should become tasks.
Guardrails
- Do not make Rabbithole a required runtime dependency for generated docs, skills, or SET.
- Do not treat Rabbithole canvas state as source of truth.
- Do not paste secrets, private profiles, or sensitive local files into Rabbithole unless the user explicitly approves.
- Prefer seed docs over huge raw files.
What ships with it
2 files 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.
- 9d ago First seen · 61 lines · 69 tokens per session scan A 97294ded6286
rabbithole-doc-exploration is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 618 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
lookup-warn
Get context warnings for a file based on its extension and name. Surfaces known gotchas before the user hits them. Triggers on: warn me, gotchas, pitfalls, what should I watch out for, check this file.
a-unslop-code
Finds what makes source code read as AI-written and points you at the parts that actually ship bugs. Sorts every tell into three buckets and fixes them in that order: bugs (swallowed errors, a made-up API, a left-in "rest of the code" stub), substance (tutorial-shaped boilerplate, over-engineering, code that ignores…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
memstack-marketing-webinar-script
Use this skill when the user says 'webinar script', 'webinar', 'live presentation', 'teach-to-sell', or needs a timestamped presentation script with slide notes, presenter cues, and replay email sequence. Do NOT use for launch plans or static sales page copy.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.