Atomic Agent is a local-first AI agent that runs its control loop and state on a user's machine while using local or cloud models. It drives browsers, edits files, runs approved commands, remembers context, schedules follow-ups, and connects to external tools, with the catalogue providing skills for its use.
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 AtomicBot-ai/atomic-agent --skill pandocgit clone --depth 1 https://github.com/AtomicBot-ai/atomic-agentWrote 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/atomicbot-ai/atomic-agent/pandoc)<a href="https://agentmods.dev/skills/atomicbot-ai/atomic-agent/pandoc"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/pandoc/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/atomicbot-ai/atomic-agent/pandoc"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/pandoc.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 | $0.00045 | $0.00846 |
| Opus 5.5 | $0.00018 | $0.00338 |
| Sonnet 5.5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
pandoc 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pandoc
Convert documents between formats with the universal
pandoc CLI. Input/output formats are inferred from file
extensions; override with -f <from> / -t <to> when needed.
PDF output requires a LaTeX engine (or --pdf-engine). Markdown/HTML/DOCX/EPUB
conversions need only pandoc itself.
Setup health check (run first, every session)
Verify with one solo step:
[{ "tool": "os.shell.run", "args": { "cmd": "pandoc", "args": ["--version"] } }]
Outcome map:
exit 0+ version → ready, proceed.command not found: pandoc→ enter Setup playbook → "pandoc missing".- PDF target fails with
pdflatex not found→ enter Setup playbook → "PDF engine missing".
Setup playbook (when prerequisites are missing)
pandoc missing
Reply (solo reply step):
"
pandocis not installed. I can install it:brew install pandoc. Install it?"
On yes:
[{ "tool": "os.shell.run", "args": { "cmd": "brew", "args": ["install", "pandoc"] } }]
On Linux: apt-get install pandoc.
PDF engine missing
PDF output needs a TeX engine. Offer the lightweight option:
"PDF export needs a TeX engine. I can install:
brew install --cask basictex(or the lightweightbrew install tectonic). Which do you prefer?"
tectonic is simplest (pandoc in.md -o out.pdf --pdf-engine=tectonic).
When to use
- "Convert this Markdown to DOCX / PDF / HTML", "turn this HTML into Markdown".
- "Make an EPUB from these chapters", "export notes to a Word doc".
When NOT to use
- Reading a document's text — use
os.fs.read_document. - Editing PDFs structurally (merge/split) — use the
pdfskill. - Spreadsheet conversion — use the
xlsxskill.
Common operations
All examples invoke os.shell.run with cmd: "pandoc". Outputs go to the
session working directory; the approval gate surfaces each write.
| Goal | args |
|---|---|
| Markdown → DOCX | ["notes.md", "-o", "notes.docx"] |
| Markdown → PDF | ["notes.md", "-o", "notes.pdf", "--pdf-engine=tectonic"] |
| Markdown → standalone HTML | ["notes.md", "-s", "-o", "notes.html"] |
| DOCX → Markdown | ["report.docx", "-o", "report.md"] |
| HTML → Markdown | ["page.html", "-f", "html", "-t", "gfm", "-o", "page.md"] |
| Many MD → one EPUB | ["ch1.md", "ch2.md", "-o", "book.epub", "--toc"] |
| With a table of contents | append ["--toc", "--toc-depth=2"] |
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.
- 1mo ago First seen · 88 lines · 45 tokens per session scan A 41ea26062bb5
pandoc is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (3,431 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 846 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
hatch3r-api-spec
Generates and validates OpenAPI specifications from codebase. Covers endpoint design, schema validation, and documentation generation.
api2pdf-automation
Automate Api2pdf tasks via Rube MCP (Composio). Always search tools first for current schemas.
boldsign-automation
Automate Boldsign tasks via Rube MCP (Composio). Always search tools first for current schemas.
api2pdf-automation
Automate Api2pdf tasks via Rube MCP (Composio). Always search tools first for current schemas.
pdf-extract
Extract plain text from a PDF document.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.