Borrowing it
Nothing to install: this file belongs to katopz/katgpt-rs. 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/katopz/katgpt-rs/develop/.agents/skills/research/SKILL.mdgit clone --depth 1 https://github.com/katopz/katgpt-rsWrote 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/skills/katopz/katgpt-rs/research)<a href="https://agentmods.dev/skills/katopz/katgpt-rs/research"><img src="https://agentmods.dev/badge/skills/katopz/katgpt-rs/research/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/skills/katopz/katgpt-rs/research"><img src="https://agentmods.dev/badge/skills/katopz/katgpt-rs/research.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 | $0.00197 | $0.20195 |
| Opus 5.5 | $0.00079 | $0.08078 |
| Sonnet 5.5 | $0.00039 | $0.04039 |
| Haiku 4.5 | $0.00020 | $0.02020 |
Grade C, and why
research scanned grade C with 2 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
5. **Cleanup is part of the task:** when the verdict/note/plan is committed, `rm -rf .raw/<repo>` (or the whole `.raw/`). A finished research task with a live `.raw/` entry is an unfinished task. If a session dies mid-ta Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `katgpt-rs/crates/katgpt-dec/src/` | `operators.rs` (`exterior_derivative` d, `codifferential` δ, `hodge_laplacian` Δ), `hodge.rs` (`hodge_decompose`, `betti_numbers`, `harmonic_projector`), `flow.rs` (`DecFlowField`), How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Workflow — Modelless Inference, Freeze/Thaw, Latent-to-Latent
This repo (katgpt-rs) + riir-ai (freeze/thaw runtime + adaptive NPCs + game systems) + riir-chain (neuro-symbolic chain transport, LatCal) + riir-neuron-db (NeuronShard, BLAKE3/Merkle, freeze/thaw envelope) ship runtime + latent-space operations. The inference substrate (weights, quant formats, kernels, encoders, loaders) lives in riir-infer; decision-engine serving + comparison (calibration, abstention, arenas) lives in riir-reflex — both opened public 2026-09-23 as the first sanctioned Research-003 exceptions. Training-method research lives in riir-train. If a paper's value is its training loop → riir-train (see §3.5 Path 0.5 — applicable training papers get a Plan, not a lazy redirect). If its value is a latent-space insight, a routing trick, a freeze/thaw pattern, a chain-commitment bridge, a neuron-shard primitive, or a modelless inference primitive → distill here. If it's about how trained weights are REPRESENTED and run (quant, kernels, encoder forwards, loaders) → riir-infer; if it's about how a MODELLESS decision is SERVED (calibration, abstention, comparison arenas) → riir-reflex; if it's a TRAINED-ENCODER serving arm (encoder lane product, per-suite winners/vessels, serving posture) → riir-rethink (private forever — reflex gets at most an owner-gated public comparison lane).
When to use
Reading/fetching/summarizing ML/AI/systems papers · deciding which repo a paper belongs to · creating .research/ notes or .plans/ files · implementing modelless inference primitives · designing freeze/thaw cycles, adapter hot-swap, runtime adapter routing · designing latent-to-latent ops (dot-product projections, sigmoid gating, manifold geometry, spectral methods) · designing MMORPG-scale game AI (thousands of concurrent NPCs, 20Hz tick, fog-of-war, emergent social/economic behavior).
Do NOT activate for: pure refactor, bug fixes with no research angle, or ordinary feature work.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · -11 lines 9863df773da5
- 22d ago Changed · +13 lines 51beeafd57f8
- 26d ago Changed 29d190cc2d36
- 28d ago Changed 9fb04628f92f
- 1mo ago Changed · +12 lines · +17 tokens per session 836376b0e1d7
- 1mo ago Changed · +30 lines · +20 tokens per session a21ffa248ce0
- 1mo ago Changed f9770188c39e
- 1mo ago Changed · -2 lines c217d6f40340
- 1mo ago Changed · +1 lines 2de80c51eeff
- 1mo ago First seen · 387 lines · 160 tokens per session scan C b6ce05c55e0d
research is a skill published in the GitHub repository katopz/katgpt-rs (140 stars, last pushed today), licensed MIT. It adds 197 tokens to every session and 20,195 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…