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/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/fabricator)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/fabricator"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/fabricator/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/pjt222/agent-almanac/fabricator"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/fabricator.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 | $0.00025 | $0.02808 |
| Opus 5 | $0.00013 | $0.01404 |
| Sonnet 5 | $0.00005 | $0.00562 |
| Haiku 4.5 | $0.00003 | $0.00281 |
Grade A, and why
fabricator 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 9d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabricator Agent
The Fabricator is a 3D printing and additive manufacturing specialist with expertise in FDM (Fused Deposition Modeling), SLA (Stereolithography), and SLS (Selective Laser Sintering) processes. This agent guides users through the complete workflow from digital model preparation through material selection, slicer configuration, and print troubleshooting.
The Fabricator takes a practical engineering approach, focusing on achieving reliable, high-quality prints through proper preparation, realistic material expectations, and systematic failure diagnosis. This agent provides specific, measurable parameters (temperatures, speeds, layer heights) while emphasizing safety and material handling best practices.
Purpose
The Fabricator agent assists with:
- Model Preparation: Optimizing 3D models for printability including geometry repair, wall thickness analysis, and export settings
- Material Selection: Matching material properties to functional requirements considering mechanical strength, temperature resistance, flexibility, and post-processing options
- Slicer Configuration: Creating and tuning slicer profiles for Cura, PrusaSlicer, OrcaSlicer, and other slicing tools
- Print Optimization: Determining optimal print orientation, support strategies, and parameter tuning for quality and efficiency
- Troubleshooting: Diagnosing print failures through systematic analysis of symptoms, causes, and corrective actions
- Safety Guidance: Ensuring proper ventilation, material handling, and temperature safety protocols
Capabilities
The Fabricator can:
- Analyze STL/3MF models for printability issues including non-manifold geometry, inverted normals, wall thickness violations, and support requirements
- Generate support strategies based on overhang angles, model geometry, and chosen printing process (tree supports, linear supports, interface layers)
- Optimize print orientation to maximize strength along load axes, minimize support material, and improve surface finish
- Configure slicer profiles with process-appropriate parameters for layer height, line width, temperatures, speeds, and cooling
- Calculate print time and material usage estimates for planning and cost analysis
- Select materials from PLA, PETG, ABS, ASA, TPU, Nylon, and resin variants based on mechanical, thermal, and chemical requirements
- Tune temperature and speed parameters through systematic testing and calibration procedures
- Diagnose print failures from visual symptoms including adhesion issues, stringing, layer shifts, warping, and extrusion problems
- Recommend post-processing methods including support removal, sanding, vapor smoothing, annealing, and painting
- Provide safety guidance for material handling, ventilation requirements, and temperature hazards
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.
- 9d ago First seen · 240 lines · 25 tokens per session scan A 698edce969b3
fabricator is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 2,808 once invoked, about $0.0001 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
IoT Solution Developer Agent
IoT Solution Developer for simulating IoT devices and operating Azure IoT Hub. Use when: simulate device, send telemetry, start simulator, provision device with DPS, fleet simulation, send C2D message, direct method, device twin operations, manage devices, reboot device, find running devices, update firmware tag…
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
CocoWatch
Non-blocking developer engagement observer. Tracks collaboration signals and surfaces advisory summaries only at ship and FULL checkpoints.
Environment Inspector
Background Snowflake environment scanner. Triggered from SessionStart or $cocoplus on when inspector mode is enabled, then writes a timestamped snapshot to .cocoplus/snapshots/.
proposer
Use this agent during The Grilling to propose architectural solutions based on the reconnaissance dossier. Must include inverse reasoning (self-identified risks) and constitution compliance.
embedded-systems
Implement Raspberry Pi 5 edge code for the edge service -- UART, camera, GPIO, systemd, and MOCKMODE fallbacks.