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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/dev-document)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/dev-document"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-document/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/commands/christopherlouet/claude-base/dev-document"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/dev-document.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 | $0.00000 | $0.00401 |
| Opus 5.5 | $0.00000 | $0.00160 |
| Sonnet 5.5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
dev-document 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 19d 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
Agent DEV-DOCUMENT
Code that makes an application generate office documents (export endpoints, invoices, report jobs).
Request context
$ARGUMENTS
Objective
Write the code that generates documents in the requested format (PDF, DOCX, XLSX, PPTX) inside the project. Choose the library suited to the format and the project's language.
For a one-off file Claude writes or edits itself (a memo, a filled-in form, a reviewed contract), Anthropic's docx / pdf / xlsx / pptx skills fit better: see docs/recipes/recommended-vendor-skills.md.
Workflow
- Identify the target format (PDF, DOCX, XLSX, PPTX)
- Choose the library (puppeteer/reportlab for PDF, docx/python-docx, exceljs/openpyxl, pptxgenjs/python-pptx)
- Prepare the content (title, sections, data, style)
- Separate data from formatting
- Generate the document with metadata (author, date, subject)
- Validate the document (opens without error, complete content, UTF-8 encoding)
Expected output
- Document generated in the requested format
- Reusable and configurable generation code
- Validation that it opens in the target software
Related agents
| Agent | When to use it |
|---|---|
/doc:doc-generate |
Technical documentation (Markdown) |
/doc:doc-api-spec |
API specification (OpenAPI) |
/biz:biz-pitch |
Pitch deck presentation |
/growth:growth-analytics |
Analysis report with data |
IMPORTANT: Always ask for the desired format if not specified.
IMPORTANT: Check that dependencies are installed before generating.
YOU MUST generate a document that opens correctly in the target software.
NEVER hardcode file paths or data.
Think hard about the formatting best suited to the content and target audience.
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.
- 19d ago Changed · +2 lines 7c2cd8ad855a
- 1mo ago First seen · 48 lines · 0 tokens per session scan A 03ad035a42d3
dev-document is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 401 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 2026-09-03.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
migrate
Generate and manage database migrations.
update-counts
Explicitly refresh public toolkit and committed marketplace source snapshots and numeric documentation.
log-decision
Append an architectural decision to the persistent decision log.
update-docs
Scan recently modified files and update the matching documentation.
backup-config
Backup Claude Code configuration files.