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 dbcls/togomcp --skill prismgit clone --depth 1 https://github.com/dbcls/togomcpWrote 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/dbcls/togomcp/prism)<a href="https://agentmods.dev/skills/dbcls/togomcp/prism"><img src="https://agentmods.dev/badge/skills/dbcls/togomcp/prism/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/dbcls/togomcp/prism"><img src="https://agentmods.dev/badge/skills/dbcls/togomcp/prism.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00209 | $0.03017 |
| Opus 5.5 | $0.00084 | $0.01207 |
| Sonnet 5.5 | $0.00042 | $0.00603 |
| Haiku 4.5 | $0.00021 | $0.00302 |
Grade A, and why
prism 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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRISM — Predicate-defined, Reproducible, Identifier-bridged, Set-intersection Mining
PRISM answers "what entities are common to property set A and property set B?" on linked open data without relying on recall. A remembered list of candidates is a hypothesis, not a set. PRISM replaces hand-seeded lists with reproducible predicate chains, then triangulates weak axes across multiple evidence sources so the intersection does not silently collapse.
Before you begin
- Files under
references/are fetched withget_workflow(name="prism", path="references/...")(when this skill is installed locally, read them as files instead). - Call
TogoMCP_Usage_Guidefirst, and run its GATE 0 classification. - Read
references/sparql-templates.md— parameterized queries for every phase (hierarchy expansion, GO→UniProt, PubTator co-occurrence, ClinVar gene-anchored significance, ChEMBL targets, Reactome membership, TogoID bridging). - Read
references/worked-example.mdfor a full end-to-end run with a filled-in provenance ledger.
When to use vs. not
Use PRISM when the question is an intersection of properties ("both A and B", "common to", "druggable target for disease", "shared genes", "overlap between"). Do not invoke the full machinery for a single-fact lookup ("what is the UniProt ID of CETP?") or a single-axis enumeration ("list genes in pathway X") — those are ordinary TogoMCP queries. The tell for PRISM is two or more constraints of different kinds that must be satisfied simultaneously.
The PRISM mnemonic → five phases
P — Pose as sets & Predicate-define each axis (kill recall)
R — Reach the full hierarchy (transitive closure)
I — Integrate multi-source evidence (triangulate weak axes)
S — Stitch by stable ID & intersect (set algebra)
M — Measure actionability & audit provenance (stratify + ledger)
Do the phases in order. The two most-skipped, most-damaging-to-skip steps are R (hierarchy expansion) and I (triangulation). Skipping R silently under-covers a set; skipping I lets a single biased source collapse the intersection.
What ships with it
2 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.
- 1mo ago Changed · +4 lines 2983aedad7e2
- 1mo ago First seen · 158 lines · 209 tokens per session scan A 3260baaed519
prism is a skill published in the GitHub repository dbcls/togomcp (19 stars, last pushed yesterday), licensed MIT. It adds 209 tokens to every session and 3,017 once invoked, about $0.0008 per session on Opus 5.5. 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 skills, from other repositories
open-ontologies
AI-native ontology engineering using 110 MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
post-cortex-memory
Long-term project memory through the post-cortex MCP server (tools named session, semanticsearch, updateconversationcontext, assemblecontext, queryconversationcontext, getstructuredsummary, manageworkspace, manageentity, admin). Use it whenever those tools are available and the work could benefit from what was learned…
ml_inference_optimization
This document describes the Leeroopedia MCP tools available during the with-KB benchmark run. It is a standalone reference and is not fed to the agents automatically.
leeroopedia-mcp
Use Leeroopedia MCP to fetch grounded ML/AI best practices, build and review ML plans, debug failures, verify code/math correctness, and expand KB citations via getpage.
midmem-research-tracker
Keep the repo's RESEARCH.md ledger current from the research ingestions already in the MidMem store: for every unevaluated weekly research ingestion, evaluate each paper's feasibility and applicable improvement for MidMem, and record it as Paper (cite + link) · Finding (the empirical claim that matters) · Decision…
sematyp
SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning.