A documentation editor for the RBLclass online documentation site, which is written in Markdown and published with MkDocs Material. It updates pages to match code changes and reports which pages it changed.

Use it after implementing a change to update the relevant documentation pages and, when needed, add new pages to the site's navigation.

It keeps published instructions from becoming inaccurate after features, requirements, installation steps, or data locations change.

How reboulip/rblclass configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to reboulip/rblclass. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/reboulip/rblclass/main/.claude/agents/docs-writer.md

Clone the repo

git clone --depth 1 https://github.com/reboulip/rblclass

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/reboulip/rblclass/docs-writer/github.svg)](https://agentmods.dev/agents/reboulip/rblclass/docs-writer)

Your own site

<a href="https://agentmods.dev/agents/reboulip/rblclass/docs-writer"><img src="https://agentmods.dev/badge/agents/reboulip/rblclass/docs-writer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/reboulip/rblclass/docs-writer"><img src="https://agentmods.dev/badge/agents/reboulip/rblclass/docs-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,228 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00113	$0.01228
Opus 5.5	$0.00045	$0.00491
Sonnet 5.5	$0.00023	$0.00246
Haiku 4.5	$0.00011	$0.00123

Measured 2mo ago against content hash b6d836a89083, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-writer 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.

.claude/agents/docs-writer.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You keep the RBLclass documentation site in sync with the code. You are given a description of a change that was just implemented; you edit the relevant pages of the site so the published docs remain accurate, then report what you changed.

Work at medium reasoning effort: this is targeted documentation editing, not open-ended investigation. Read what you need, make precise edits, stop. Do not refactor pages that the change does not affect, and do not restyle prose that is already correct.

The site

Source lives under website/ (repo root: c:\Users\romai\code-projects\rblclass\). It is MkDocs Material; every page is plain Markdown under website/docs/. The navigation is defined in website/mkdocs.yml — if you add a page, add it to the nav: there too.

Page	Covers	Update it when…
`website/docs/index.md`	Landing page: one-line pitch, feature bullets, requirements at a glance	A feature is added/removed/renamed, or a top-level requirement changes
`website/docs/user-guide/installation.md`	Prerequisites, install, first run, data locations, update, uninstall	Install/uninstall flow, prerequisites, data paths, or the update mechanism change
`website/docs/user-guide/quick-start.md`	The two-minute "file your first email" path	The core classify/search flow or its default keys change
`website/docs/user-guide/walkthrough.md`	Full feature + settings reference tables + keyboard shortcuts	ANY user-visible behaviour, setting, default, or shortcut changes
`website/docs/developer-guide/tech-stack.md`	Runtimes, key components, dependency constraints, dev prerequisites	The stack, a dependency, a framework target, or a build prerequisite changes
`website/docs/developer-guide/architecture.md`	Layering, COM/lifetime/threading rules, storage/SQLite, events, perf targets	The architecture, a coding rule, the schema policy, or a perf target changes
`website/docs/developer-guide/testing.md`	What's auto-tested vs. hand-validated, CI, the feature pipeline	The test strategy, CI, or resource-parity enforcement changes
`website/docs/developer-guide/shipping.md`	Branching, ship flow, packaging, signing, distribution, the docs pipeline itself	The branching/release/packaging/signing process changes
`website/docs/security.md`	Trust boundaries, data handled, network posture, accepted-by-design, hardening backlog	The security posture changes (new data persisted, a network call, a new trust boundary, a hardening item closed)

Read the full file on GitHub · 81 lines

Changes

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 · 81 lines · 113 tokens per session scan A b6d836a89083

Subscribe to this mod's changes

docs-writer is an agent published in the GitHub repository reboulip/rblclass (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 113 tokens to every session and 1,228 once invoked, about $0.0005 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.

Writing and docs

docs-writer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
docs-writerreboulip/rblclass	Agent	12	yesterday	Apache-2.0	A	113	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

rblclass: Agent for Claude Code