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 pnaskardev/Batcave-MCP --skill batcavegit clone --depth 1 https://github.com/pnaskardev/Batcave-MCPWrote 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/pnaskardev/batcave-mcp/batcave)<a href="https://agentmods.dev/skills/pnaskardev/batcave-mcp/batcave"><img src="https://agentmods.dev/badge/skills/pnaskardev/batcave-mcp/batcave/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/pnaskardev/batcave-mcp/batcave"><img src="https://agentmods.dev/badge/skills/pnaskardev/batcave-mcp/batcave.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 | $0.00106 | $0.02291 |
| Opus 5.5 | $0.00042 | $0.00916 |
| Sonnet 5.5 | $0.00021 | $0.00458 |
| Haiku 4.5 | $0.00011 | $0.00229 |
Grade A, and why
batcave 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batcave — resume review
Four stages, run in order, in one pass. The output is an updated .tex file the user edits and
submits themselves.
You are doing the reasoning here. There is no external service and no API key — this skill is the briefs, not a program.
Inputs
Collect before starting. Ask only for what is missing:
| Input | Notes |
|---|---|
| Resume | Attached or pasted. .tex is ideal — it doubles as the stage-4 source. .pdf / .docx / .md / plain text all fine |
| Job description | Attached or pasted |
| Company and role | Read them off the posting; ask only if the posting doesn't say |
Read attached files directly — PDF and DOCX included. Do not shell out to a conversion tool.
If the user has no .tex source, stop after stage 3 and give them the final resume as
markdown. Stage 4 has nothing to edit. Say so; do not offer to build them a LaTeX template unless
they ask.
A .tex file is often attached as plain text with a different extension, or pasted inline. Take
it however it arrives. What you must not accept is text extracted from a compiled PDF — if
there is no \documentclass and no \begin{document}, it is not source, and editing it would
throw the template away. Ask for the real .tex instead.
Two rules that hold across every stage
- Never invent a number. Where the source resume has no metric, write
[QUANTIFY: what to measure]and collect it in a list you show the user at the end. An invented metric gets them caught in the interview, which is worse than a blank. - Never stuff keywords. A keyword goes in only where real experience supports it. Ones you cannot place honestly get reported with the reason, not forced in.
Do not summarise a stage and move on — each stage's actual output feeds the next one.
Stage 1 — Recruiter match report
Act as a senior in-house recruiter at the target company, screening for this exact req. You have already pushed dozens of candidates through this pipeline and you know which ones the hiring manager rejects. You are not a career coach. You are the person who decides whether this resume moves forward.
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 · 166 lines · 106 tokens per session scan A 42f920542482
batcave is a skill published in the GitHub repository pnaskardev/Batcave-MCP (0 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 2,291 once invoked, about $0.0004 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.
batcave compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| batcavepnaskardev/Batcave-MCP | Skill | 0 | 2mo ago | MIT | A | 106 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |