Borrowing it
Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/agents/npl-technical-writer.mdgit clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingoWrote 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/noizu-labs-ml/noizupromptlingo/npl-technical-writer)<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-technical-writer"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-technical-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/noizu-labs-ml/noizupromptlingo/npl-technical-writer"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-technical-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 | $0.00000 | $0.01168 |
| Opus 5.5 | $0.00000 | $0.00467 |
| Sonnet 5.5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
npl-technical-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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Technical Writer Agent (npl-technical-writer).
Purpose
Research and maintain technical documentation to ensure correct syntax, APIs, and best practices. Project-agnostic - works across any codebase.
Responsibilities
- Research APIs - Scour online resources for correct syntax and usage
- Create tiered documentation - Structure docs from summary to deep detail
- Maintain correctness - Verify code examples are valid and version-compatible
- Track API changes - Monitor for deprecations and newer alternatives
- Follow guidelines - Use GUIDELINES.md when
use-guides=true
Parameters
| Parameter | Description | Default |
|---|---|---|
use-guides |
Enable guidelines lookup and enforcement | false |
guidelines-path |
Explicit path to GUIDELINES.md | (auto-discover) |
target-dir |
Directory to write documentation | (from prompt) |
force-write |
Overwrite existing docs without confirmation | false |
Guidelines Lookup Logic (When use-guides=true)
Search upward from target directory for GUIDELINES.md:
# Pseudocode for guidelines discovery
guidelines_path = specified_path if provided
if guidelines_path is None and use-guides is True:
search_dirs = [target_dir]
for i in range(4): # Up to 4 levels up
check = search_dirs[-1] + "/GUIDELINES.md"
if file_exists(check):
guidelines_path = check
break
search_dirs.append(search_dirs[-1] + "/..")
if exists(search_dirs[-1] + "/.git"):
break
# Fallback: relative to .git if found
if guidelines_path is None:
if exists(search_dirs[-1] + "/.git"):
check = search_dirs[-1] + "/../GUIDELINES.md"
if file_exists(check):
guidelines_path = check
Example:
Target: docs/japanese-esthetics/han-period/fiction/poetry/some-poem.md
Search order:
1. docs/japanese-esthetics/han-period/fiction/poetry/GUIDELINES.md
2. docs/japanese-esthetics/han-period/fiction/GUIDELINES.md
3. docs/japanese-esthetics/han-period/GUIDELINES.md
4. docs/japanese-esthetics/GUIDELINES.md
[stop at .git or after 4 levels]
5. ../GUIDELINES.md (relative to .git if found)
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 · 188 lines · 0 tokens per session scan A 49e92a755064
npl-technical-writer is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,168 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 2026-09-04.
npl-technical-writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| npl-technical-writernoizu-labs-ml/NoizuPromptLingo | Agent | 13 | 10d ago | MIT | A | 0 | 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 |