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.
npx agentmods add agents/bluzir/claude-pipe/generator.templategit clone --depth 1 https://github.com/bluzir/claude-pipeWhat 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 | $0.00004 | $0.01021 |
| Opus 5 | $0.00002 | $0.00511 |
| Sonnet 5 | $0.00001 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
{artifact}-generator 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 3d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{Artifact} Generator
Purpose
Generate {artifact type} from synthesized data, ensuring quality, traceability, and adherence to style guidelines.
Context
Agent receives:
synthesis_path: Path to synthesis.yaml (L2 data)template: Template or structure guidelines (optional)style: Style/tone requirements (optional)output_path: Where to write artifact
Supporting data:
plan: Original plan with goals/constraintsquality: Quality gate results (if available)
Instructions
1. Load Source Data
- Read synthesis from
synthesis_path - Read plan for context and constraints
- Read quality report for caveats (if exists)
2. Structure Planning
Based on synthesis data:
- Identify main sections/chapters
- Map findings to sections
- Determine narrative flow
- Note gaps or weak areas (from quality report)
3. Content Generation
For each section:
-
Ground in Data
- Use only facts from synthesis
- Every claim must trace to a finding
- Apply grounding-protocol skill
-
Generate Content
- Follow template structure (if provided)
- Match requested style/tone
- Use clear, direct language
-
Quality Filter
- Apply anti-cringe skill
- Remove AI-typical phrases
- Ensure natural flow
4. Assembly & Review
- Combine sections into final artifact
- Add metadata header
- Include source references
- Final quality check
Constraints
- Every claim must be traceable to synthesis data
- No hallucinated facts or statistics
- No AI-typical filler phrases (per anti-cringe)
- Follow provided template exactly (if given)
- Include "Generated by" attribution
Output Structure
For Markdown Reports
---
title: "{Artifact Title}"
generated_at: "{timestamp}"
source: "synthesis.yaml"
agent: "{artifact}-generator"
---
# {Title}
## Executive Summary
{2-3 paragraph summary of key findings}
## Section 1: {Topic}
{Content grounded in synthesis findings}
> Source: {finding_id} from {source_url}
## Section 2: {Topic}
...
## Conclusion
{Summary and implications}
---
## Sources
- [Source 1](url) - Finding IDs: 001, 003, 007
- [Source 2](url) - Finding IDs: 002, 005
## Metadata
- Generated: {timestamp}
- Synthesis version: {version}
- Quality gate: {PASS|WARN}
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.
- 3d ago First seen · 189 lines · 0 tokens per session scan A da2981f75814
{artifact}-generator is an agent published in the GitHub repository bluzir/claude-pipe (89 stars, last pushed 6mo ago), licensed MIT. It adds 4 tokens to every session and 1,021 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.