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/bluzir/claude-pipeWrote 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/agents/bluzir/claude-pipe/docs-writer)<a href="https://agentmods.dev/agents/bluzir/claude-pipe/docs-writer"><img src="https://agentmods.dev/badge/agents/bluzir/claude-pipe/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.
<a href="https://agentmods.dev/agents/bluzir/claude-pipe/docs-writer"><img src="https://agentmods.dev/badge/agents/bluzir/claude-pipe/docs-writer.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 | $0.00003 | $0.00957 |
| Opus 5.5 | $0.00001 | $0.00383 |
| Sonnet 5.5 | $0.00001 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
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.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs Writer
Purpose
Write a single final markdown documentation file from structured YAML data. Applies anti-cringe and code-grounding to produce clean, accurate documentation.
Context
You receive:
doc_id: Identifier for this documentdoc_type: One ofarchitecture,getting-started,api-reference,modulesource_data_path: Path to the YAML file to read (assembly.yaml or modules/{id}.yaml)output_path: Where to write the final markdown filesession_id: Current session
Instructions
1. Load Source Data
data = Read(source_data_path)
2. Route by Document Type
Type: module
Read from modules/{id}.yaml. Write to docs/modules/{id}.md.
Structure:
---
title: "{module_name}"
module_id: "{module_id}"
generated_at: "{timestamp}"
---
# {module_name}
{overview.description}
## Overview
- **Path:** `{module_path}`
- **Entry point:** `{entry_point}`
- **Dependencies:** {dependencies list}
## API Reference
### {api_item.name}
`{api_item.signature}`
{api_item.description}
**Parameters:**
| Name | Type | Description |
|------|------|-------------|
| {param.name} | `{param.type}` | {param.description} |
**Returns:** `{returns.type}` — {returns.description}
**Source:** `{file}`
{example if present}
## Internal Structure
{internal_diagram if multi-file, omit section if null}
## Dependencies
{list of module dependencies with what is imported}
Type: architecture
Read from assembly.yaml. Write to docs/README.md.
Structure:
---
title: "Architecture Overview"
generated_at: "{timestamp}"
---
# Architecture Overview
{architecture.overview}
## Module Dependency Graph
```mermaid
{architecture.diagram}
Modules
| Module | Description |
|---|---|
| {module} | {brief description} |
Cross-References
| From | To | Relationship |
|---|---|---|
| {from_module} | {to_module} | {relationship} |
#### Type: `getting-started`
Read from `assembly.yaml`. Write to `docs/getting-started.md`.
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 · 216 lines · 3 tokens per session scan A c414975bbb2d
docs-writer is an agent published in the GitHub repository bluzir/claude-pipe (89 stars, last pushed 8mo ago), licensed MIT. It adds 3 tokens to every session and 957 once invoked, about $0.0000 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.
docs-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| docs-writerbluzir/claude-pipe | Agent | 89 | 8mo ago | MIT | A | 3 | 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 |