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 skills add cyanheads/pubchem-mcp-server --skill techniquesgit clone --depth 1 https://github.com/cyanheads/pubchem-mcp-serverWrote 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/cyanheads/pubchem-mcp-server/techniques)<a href="https://agentmods.dev/skills/cyanheads/pubchem-mcp-server/techniques"><img src="https://agentmods.dev/badge/skills/cyanheads/pubchem-mcp-server/techniques.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 | $0.00079 | $0.00487 |
| Opus 5 | $0.00039 | $0.00244 |
| Sonnet 5 | $0.00016 | $0.00097 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
techniques 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 8d 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.
This is a copy
100% identical to techniques — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Overview
A directory of cross-cutting techniques for shaping what a handler returns and how a client retrieves it — patterns that don't belong to a single API surface. Each entry is a self-contained reference under references/: the problem it solves, when to reach for it (and when not to), and how to apply it with current framework primitives.
These are patterns, not new primitives — they compose tool(), output/format() shaping, ctx.state, and the existing helpers. Where a technique has (or will have) a dedicated helper, its reference says so and links the tracking issue.
Techniques
| Technique | Path | Use when |
|---|---|---|
| Outline-on-overflow | references/outline-on-overflow.md |
A single tool call returns one document-shaped payload too big to inline (e.g. a ~130KB record), and you want an honest section outline + a re-call contract instead of truncating. |
Adding a technique
One file under references/, one row above. A technique earns a place here when it's a reusable response/retrieval pattern that (a) spans more than one tool or server and (b) isn't already covered by an api-* reference. Keep the reference concise: problem → when-to-use → how-to with current primitives → helper status. Bump metadata.version on any change (skill-versioning policy).
Related
design-mcp-server— choosing the tool surface and output shapes up front.add-tool— thetool()builder,format()⟷structuredContentparity, matching response density to context budget.api-canvas—spillover(), the row-collection sibling of outline-on-overflow.
What ships with it
1 file 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.
- 8d ago First seen · 33 lines · 79 tokens per session scan A 8f01d620e53c
techniques is a skill published in the GitHub repository cyanheads/pubchem-mcp-server (9 stars, last pushed 17d ago), licensed Apache-2.0. It adds 79 tokens to every session and 487 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to techniques, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
pepflex
Use when working with PepFlex for in silico peptide screening and evolutionary optimization. Handles peptide population management, mutation, crossover, custom evaluation pipelines, and multi-round evolutionary simulation.
chem-brainstorm
Use at the start of any computational chemistry task to structure thinking, map available tools, and generate concrete hypotheses. Covers molecule evaluation, hypothesis building, reaction assessment, and pipeline design. Flexible guide — adapt depth to problem complexity.
generative-design
Use when designing or evaluating generative models for de novo drug/molecule design. Covers molecular generation theory and evaluation (MOSES/GuacaMol), SELFIES + language models, RL-based optimization with REINVENT 4, JT-VAE and graph-based generation, and structure-based 3D generation (DiffSBDD, Pocket2Mol…
homology-modeling
Use when building a 3D protein structure from sequence (no experimental structure available). Covers comparative homology modeling (MODELLER), AI-based prediction (AlphaFold2/ColabFold/ESMFold), model quality assessment (DOPE, pLDDT, Ramachandran), template search (HHblits, BLAST, Biopython), and structure preparation…
lit-rescue
Last-resort skill. Invoke when no obvious or coherent solution is available and hallucination risk is high. Searches peer-reviewed literature and validated sources (Perplexity, bioRxiv, PubMed) before attempting an answer. Generalist — applies to any domain.
uncertainty-qsar
Use when building QSAR/ML models that need calibrated uncertainty estimates. Covers epistemic vs aleatoric uncertainty theory, conformal prediction with MAPIE (guaranteed coverage), Gaussian processes with Tanimoto kernel, deep uncertainty (MC dropout, deep ensembles, Laplace), and applicability domain (AD)…