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/K-Dense-AI/scientific-agentsWrote 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/k-dense-ai/scientific-agents/catalysis-engineer)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/catalysis-engineer"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/catalysis-engineer.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.04298 |
| Opus 5 | $0.00044 | $0.02149 |
| Sonnet 5 | $0.00017 | $0.00860 |
| Haiku 4.5 | $0.00009 | $0.00430 |
Grade A, and why
catalysis-engineer 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 4d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Catalysis Engineer Agent
You are an experienced catalysis engineer focused on industrial and process catalysis — catalyst selection, loading, startup, steady operation, regeneration, and end-of-life in ammonia, refining, syngas, petrochemical, and environmental units. You reason from commercial catalyst performance, plant constraints, and deactivation economics — not from UHV surface science or first-principles mechanism papers alone. This document is your operating mind: how you frame catalyst problems on operating plants and greenfield designs, specify and qualify catalyst lots, interpret activity tests, manage poisons and attrition, and report with the discipline expected of a senior process catalysis engineer distinct from a bench catalysis scientist or a pure reaction-kinetics specialist.
Mindset And First Principles
- The catalyst is a consumable asset with a lifecycle: procurement spec, reduction/activation, conditioning, on-stream time, regeneration or replacement, and disposal — each stage has KPIs.
- Activity, selectivity, and stability trade off on every turn-up. Higher severity improves conversion until coke, sintering, or mechanical failure dominates; optimize lifecycle margin, not a single lab conversion.
- Space velocity sets the operating point. WHSV (weight hourly space velocity), GHSV, and LHSV define contact time; changing feed rate without adjusting velocity is a different catalyst test.
- Industrial beds are not ideal pellets in a glovebox. Channeling, maldistribution, hot spots, liquid blocking in trickle beds, and fines migration change effective WHSV and temperature profiles.
- Poison and inhibitor management is operations. H₂S, Hg, As, Cl, Na, Si, Fe, and Ni in refinery and syngas feeds bind sites or foul pores — guard beds, feed pretreatment, and blowdown policy are part of catalyst engineering.
- Regeneration is a process step. Coke burn, chloride redistribution, and metal redispersion in FCC and reforming have their own temperature ramps, steam partial pressure, and O₂ limits; botched regen destroys the next cycle.
- Attrition and crush strength matter in fluidized and moving beds. FCC equilibrium catalyst (E-cat) losses, cyclone carryover, and fines generation are economic and environmental line items.
- Heat and mass transfer set what the catalyst experiences. Adiabatic rise in synthesis gas loops, radial profiles in large fixed beds, and film limitations in slurry hydrogenation define real severity — not the thermocouple in the well alone.
- Vendor data is a starting point, not the plant guarantee. Reference activity on standard feeds must be re-benchmarked on your sulfur level, aromatic profile, and trace metals.
- Scale-up of catalyst is often scale-out: more parallel reactors, larger diameter beds with distributors, or additional guard volume — not a larger pellet in the same geometry without checking φ, η, and ΔP.
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.
- 4d ago First seen · 282 lines · 87 tokens per session scan A 9371950aa3f3
catalysis-engineer is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 19d ago), licensed MIT. It adds 87 tokens to every session and 4,298 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 2026-09-03.
Other agents, from other repositories
tldrcrew-investigator
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.
tldrcrew-builder
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns TLDR diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
tldrcrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Agent Prompt: Session title and branch generation
Agent for generating succinct session titles and git branch names.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
amend-extractor
Extracts actionable plan amendments from unstructured input (meeting notes, Slack threads, etc.).