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/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/commands/noizu-labs-ml/noizupromptlingo/npl-update-howto-docs)<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/npl-update-howto-docs"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/npl-update-howto-docs/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/noizu-labs-ml/noizupromptlingo/npl-update-howto-docs"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/npl-update-howto-docs.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 | $0.01020 |
| Opus 5 | $0.00000 | $0.00510 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
npl-update-howto-docs 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 6d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJ-HOWTO.md — Maintenance Guide
Purpose
docs/PROJ-HOWTO.md provides task-oriented guides for the things a user will actually need to do with this project or component. Where PROJ-ARCH explains what it is and PROJ-LAYOUT where things live, HOWTO answers "how do I…?" for the likely tasks — with runnable steps.
Structure
docs/
├── PROJ-HOWTO.md # Index + short guides (keep small)
├── PROJ-HOWTO.summary.md # Companion: task list + one-line outcomes
└── howto/
├── first-hour.md # Extracted long guides, one task each
├── produce-rich-formats.md
└── ...
Selecting Tasks to Document
Prioritize, in order:
- First-hour tasks — install, configure, verify it works
- The recurring workflow — the 2-5 things users do weekly with this tool
- Non-obvious capability — powerful features hidden behind flags/config a user wouldn't guess (e.g. using
tabbing-onto track what you worked on over time; usingmedia-toolto produce syntactically rich, correct output in niche or post-training-cutoff file formats) - Sharp edges — tasks where the naive approach fails and the correct path needs stating
Skip tasks that are self-evident from --help unless the flags interact in surprising ways.
Guide Format
Each guide follows this template:
## How to: [task in the user's words]
**Goal:** [one sentence — the outcome, not the mechanism]
**Prereqs:** [installed tools, env vars, access needed — link, don't re-explain]
1. [Step with the exact command in a code block]
2. [Step]
**Verify:** [command or observation proving it worked]
**Gotchas:** [the 1-3 ways this commonly fails, each with the fix]
Rules
- Commands must be copy-paste runnable against the current code — test or trace each one during the update
- Lead with the common case; variants go under Gotchas or a short "Variations" note
- Link to PROJ-ARCH/PROJ-FAQ for why; HOWTO stays on how
- Use the user's vocabulary in headings ("How to: track what I worked on this week"), not internal module names
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.
- 6d ago First seen · 102 lines · 0 tokens per session scan A 9653b030dcd2
npl-update-howto-docs is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,020 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.