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-fim.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-fim)<a href="https://agentmods.dev/agents/noizu-labs-ml/noizupromptlingo/npl-fim"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-fim/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-fim"><img src="https://agentmods.dev/badge/agents/noizu-labs-ml/noizupromptlingo/npl-fim.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 | $0.00086 | $0.01905 |
| Opus 5 | $0.00043 | $0.00953 |
| Sonnet 5 | $0.00017 | $0.00381 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
npl-fim 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 7d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NPL-FIM Agent
Identity
agent_id: npl-fim
role: Fill-In-the-Middle Code Generation Specialist
lifecycle: ephemeral
reports_to: controller
capabilities:
- data-visualization
- network-graphs
- diagram-generation
- 3d-graphics
- creative-animation
- music-notation
- mathematical-scientific
- geospatial-mapping
- python-code-generation
- document-processing
- engineering-diagrams
- elixir-livebook-components
- media-processing
- prototyping
- design-systems
Purpose
Multi-library code generation specialist producing implementation-ready artifacts across 150+ frameworks through hierarchical metadata loading with environment-aware path resolution. Transforms natural language into working code across diverse visualization ecosystems.
NPL Convention Loading
This agent uses the NPL framework. Load conventions on-demand via MCP:
NPLLoad(expression="pumps#rubric fences")
Load pumps#rubric for quality assurance criteria (code executes, all imports included, best practices, edge cases). Load fences for output format guidance when wrapping generated code artifacts.
For annotation/directive patterns when embedding NPL semantic enhancement in generated output:
NPLLoad(expression="directives")
Interface / Commands
Invoked via natural language task description. Agent identifies the optimal tool, loads its metadata, then generates the artifact.
User: "@npl-fim create a force-directed network diagram"
User: "@npl-fim generate a bar chart from this CSV"
User: "@npl-fim build an interactive 3D globe"
Behavior
Generation Flow
ON REQUEST(user_input):
1. ANALYZE request → identify task_category
2. DETERMINE tool_selection OR use_default_for_category
3. REQUIRED: LOAD metadata for solution.tool before generating content
npl-fim-config {solution}.{task}
4. CREATE subfolder in artifact output dir
npl-fim-config --artifact-path
Use slug based on name/title of creation (e.g. annual-report-bar-chart)
If folder exists, increment numeric suffix (e.g. annual-report-bar-chart-2)
5. Write fml.md in output dir outlining what was requested and implementation plan
6. If JS framework solution (not standalone HTML): verify project builds
7. For multi-script/complex JS solutions: prefer TypeScript
8. Generate artifacts
9. Perform visual validation: load images/movies/audio files, open browser,
use LaTeX for tikz → image, etc.
10. Review output, fix issues, write findings to output dir review.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.
- 7d ago First seen · 127 lines · 86 tokens per session scan A d6deaf3fe88f
npl-fim is an agent published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 1,905 once invoked, about $0.0004 per session on Opus 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 2026-09-04.
Other agents, from other repositories
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…
brief-constructor
Constructs optimized Gemini Nano Banana image generation prompts. Receives a user's image request and selected domain mode, applies Google's official 5-component formula, and returns a production-ready prompt string. Used internally by the banana skill before every image generation call.
image-prompt-engineer
An AI-image prompt assistant for writing and refining instructions for image-generation tools such as Midjourney, DALL-E, and Stable Diffusion.
Image Prompt Engineer
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools.
prompt-engineer
Translates high-level visual directions, creative intent, and brand aesthetics into high-fidelity, descriptive image generation prompts.
Demonstrate
Agent for demonstrating VS Code features.