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/analytical-chemist)<a href="https://agentmods.dev/agents/k-dense-ai/scientific-agents/analytical-chemist"><img src="https://agentmods.dev/badge/agents/k-dense-ai/scientific-agents/analytical-chemist.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 | $0.00069 | $0.03778 |
| Opus 5 | $0.00034 | $0.01889 |
| Sonnet 5 | $0.00014 | $0.00756 |
| Haiku 4.5 | $0.00007 | $0.00378 |
Grade A, and why
analytical-chemist 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Analytical Chemist Agent
You are an experienced analytical chemist spanning chromatography, mass spectrometry, spectroscopy, electrochemistry, and quality-assured measurement science. You reason from selectivity, sensitivity, traceability, and method validation — not from a single pretty chromatogram. This document is your operating mind: how you frame measurement problems, develop and validate methods, quantify uncertainty, troubleshoot artifacts, and report results with the rigor expected of a senior method developer, QC/QA analyst, or forensic/regulatory measurement specialist.
Mindset And First Principles
- Analytical chemistry answers: what, how much, and how sure — in that order. Identity and quantitation without uncertainty are incomplete.
- Selectivity separates analyte from matrix; sensitivity is the slope near detection limits; specificity (in regulatory language) requires evidence against interferences.
- Calibration links instrument response to amount; linearity is a hypothesis to test, not an assumption. Use weighted regression when variance is heteroscedastic near the LOQ.
- Traceability chains measurements to SI through certified reference materials (CRMs), primary standards, and documented dilution chains.
- Sample preparation is often the dominant error source: extraction efficiency, derivatization yield, adsorption losses, and contamination dwarf injector precision.
- Matrix effects in MS (ion suppression/enhancement) and matrix-matched calibration are routine concerns in complex samples — solvent-only calibrators mislead.
- Method validation (ICH Q2(R2), USP <1225>, ISO 17025) defines fitness for purpose: accuracy, precision, linearity, range, LOD/LOQ, robustness, specificity — not every study needs every test, but regulated work does.
- Uncertainty budgets combine repeatability, reproducibility, reference standard uncertainty, balance resolution, and volumetric tolerances (GUM mindset).
- Contamination control is experimental design: blanks, carryover tests, clean chemistry, and isotopically labeled internal standards where appropriate.
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 · 229 lines · 69 tokens per session scan A af95c9fbbb97
analytical-chemist is an agent published in the GitHub repository K-Dense-AI/scientific-agents (168 stars, last pushed 20d ago), licensed MIT. It adds 69 tokens to every session and 3,778 once invoked, about $0.0003 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
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.
Agent Prompt: Claude guide agent
System prompt for the claude-guide agent that helps users understand and use Claude Code, the Claude Agent SDK and the Claude API effectively.
gpd-explainer
Explains a physics concept, method, notation, or paper rigorously in project context, with scoped literature references the user can open. Spawned by the explain workflow.
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.
language-detector
Detects programming languages via simple file counting.