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 agentmods add skills/kdevos12/alkyl/synkitnpx skills add Kdevos12/ALKYL --skill synkitgit clone --depth 1 https://github.com/Kdevos12/ALKYLWhat 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 | $0.00056 | $0.01085 |
| Opus 5 | $0.00028 | $0.00543 |
| Sonnet 5 | $0.00011 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
synkit 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 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.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SynKit
Graph-based Python toolkit for reaction informatics: ITS graph construction, canonicalization, AAM validation, DPO rule extraction, CRN analysis, and synthesis planning.
Paper: doi:10.1021/acs.jcim.5c02123 | JCIM 2025
When to Use This Skill
- Converting reaction SMILES → ITS graphs (NetworkX) → DPO rules (GML)
- Validating or comparing atom-to-atom mappings (AAMValidator)
- Canonicalizing reaction SMILES (CanonRSMI) or ITS graphs (GraphCanonicaliser)
- Clustering reactions by structural similarity (WL graph hash)
- Extracting and composing reaction rules (DPO formalism)
- Analyzing chemical reaction networks (Feinberg deficiency theory, Petri nets)
- Detecting autocatalysis, siphons, traps in reaction networks
- Planning synthetic routes via rule composition (SynReactor)
- Building reaction databases or curating USPTO/ChEMBL reaction data
Core Concept: ITS Graph
The Imaginary Transition State (ITS) graph merges reactant and product graphs into a single labeled multigraph:
- Nodes: atoms with attributes (symbol, charge, radical, hybridization, H count)
- Edges: bonds with attributes (bond type,
changeflag: formed / broken / unchanged)
ITS ≡ CGR (Condensed Graph of Reaction) — same structure, different naming tradition.
Quick Start
from synkit.IO import load_reaction_smiles
from synkit.Graph import ITSConstruction
from synkit.Chem import CanonRSMI, AAMValidator
# 1. Parse reaction SMILES → ITS graph (NetworkX)
rxn_smiles = "[CH3:1][OH:2].[Na:3][H:4]>>[CH3:1][O:2][Na:3].[H:4][H:5]"
its = ITSConstruction.from_reaction_smiles(rxn_smiles)
# 2. Canonicalize the reaction SMILES
canon = CanonRSMI(rxn_smiles).canonicalize()
# 3. Validate atom-atom mapping
valid = AAMValidator(rxn_smiles).is_valid()
Router — What to Read
| Task | Reference |
|---|---|
| Load reactions, format conversion (SMILES ↔ ITS ↔ GML), data I/O | references/io-conversion.md |
| Canonicalization (CanonRSMI), AAM validation, Reaction class | references/chem-standardization.md |
| ITS construction, MTG, graph canonicalization, WL hashing, subgraph search | references/graph-its.md |
| DPO rules, GML format, rule composition, SynReactor forward/retro | references/rule-dpo.md |
| CRN building, Feinberg deficiency theory, Petri nets, autocatalysis | references/crn-analysis.md |
| Synthesis planning, route construction, pathway analysis | references/synthesis-planning.md |
What ships with it
6 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 First seen · 104 lines · 0 tokens per session scan A d2e40169e0d7
synkit is a skill published in the GitHub repository Kdevos12/ALKYL (6 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 1,085 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 2026-08-31.
Other skills, from other repositories
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
tool-defs-analysis
Read-only audit of MCP definition language across an existing surface — tools, resources, prompts, server instructions. Walks every definition file and checks 16 categories the LLM reads to decide whether and how to call: voice & tense, internal leaks, audience leaks, defaults, recovery hints, field descriptions…
add-service
Scaffold a new service integration. Use when the user asks to add a service, integrate an external API, or create a reusable domain module with its own initialization and state.
add-app-tool
Scaffold an MCP App tool + UI resource pair. Use when the user asks to add a tool with interactive UI, create an MCP App, or build a visual/interactive tool.