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 skills/sunholo-data/ailang-parse/add-formatnpx skills add sunholo-data/ailang-parse --skill add-formatgit clone --depth 1 https://github.com/sunholo-data/ailang-parseWhat 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 | $0.00183 | $0.03600 |
| Opus 5 | $0.00092 | $0.01800 |
| Sonnet 5 | $0.00037 | $0.00720 |
| Haiku 4.5 | $0.00018 | $0.00360 |
Grade A, and why
add-format 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 2d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new format to AILANG Parse
When to Use
Invoke this skill any time a new input or output format is being added to AILANG Parse — no matter how the request is phrased. The cost of forgetting a surface (Pages deploys failing silently, registry out of sync with docs, SDK READMEs stale) is far higher than the cost of running through the checklist. Also use it when the user asks "what's left?" mid-rollout, to audit which surfaces are still missing.
Quick Start
- Confirm scope with user (see Before you start).
- Work through phases 1→7 in order. Do not batch phases 3+ before phases 1–2 type-check and smoke-test cleanly.
- Use the Files checklist at the end as the final PR audit.
Workflow
Adding a format hits ~20 distinct files across parser code, WASM bundle, docs, SDKs, release manifests, and deployment messaging. Skipping any one of them breaks something silently — the LaTeX/v0.15.0 rollout missed the vendor script and two Pages deploys failed before anyone noticed. Work through this list in order; do not batch steps 6-8 before 1-5 are green.
Before you start
Confirm with the user:
- Extension(s) — e.g.
.tex,.latex,.ltx - Parser strategy — deterministic (XML/text → Block ADT) or AI-assisted (PDF/image)?
- Archive wrapper? — some formats ship as
.tar.gz/.zipbundles. If yes, flag which archive tooling is missing (seestd/tar/std/gzipblocker tracked as ailang-core#156). - Will the WASM demo support it? — pure parser with no FS/AI effect = yes. FS-dependent (like multi-file
\inputresolution) = server-side only, WASM gets a single-file subset.
Set a working variable — $FMT in examples below is the lowercase short name (tex, epub, etc.).
Phase 1 — Parser (AILANG source)
- Write the parser →
docparse/services/${FMT}_parser.ail- Export a pure entry point:
export pure func parse${Fmt}(content: string) -> [Block] - Match block ADT variants from
docparse/types/document.ail; don't add new variants unless absolutely necessary. - Follow the foldl + reverse pattern from
markdown_parser.ail— see feedback_ailang_string_perf.md — neverconcat(xs, [x])in foldl.
- Export a pure entry point:
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.
- 2d ago First seen · 267 lines · 183 tokens per session scan A 0c6dd3af74a1
add-format is a skill published in the GitHub repository sunholo-data/ailang-parse (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 183 tokens to every session and 3,600 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
document-converter
Convert Office documents (PPTX, DOCX, XLSX, PDF, HTML, CSV, JSON, XML, images) to Markdown using Microsoft MarkItDown. Provides the agent with conversion strategies for academic and research workflows.
office-router
Route Office requests into the correct xlsx, docx, or pptx workflow, while preferring Slidev for new presentation drafts unless .pptx is explicitly required.
doc-converter
Universal document format converter - DOCX, PDF, Markdown, HTML, TXT.
document-processing
End-to-end document processing agent skill covering PDF manipulation (extract, merge, split, rotate, watermark, form-fill, OCR), DOCX creation and editing (templates, mail-merge, style management), XLSX spreadsheet handling (formulas, charts, pivot tables, data analysis), PPTX presentation generation (layouts, charts…
docx-architecture-audit
Audit the office-open-xml-viewer DOCX layout architecture for a single immutable layout-to-paint pipeline. Use after major DOCX layout, pagination, measurement, paint, parser-model, worker, or compatibility changes, and before declaring Issue.
office-artifacts
Use when creating, opening, reading, or editing Office artifacts such as LibreOffice-native ODT/ODS/ODP files and compatibility DOCX/XLSX/PPTX files with the officeartifact tool.