What is hypothesis-proximity-update?

A procedure for updating how closely one research hypothesis matches others using an embedding service, which represents text as numerical data.

Use it to process one hypothesis, update its proximity receipt and status, and save a revised proximity graph when the embedding service returns valid data.

It keeps the project's hypothesis-proximity records and pipeline state updated after one hypothesis is processed.

hypothesis-proximity-update — Skill for Claude Code and Codex by panjo

Install

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.

Any agent

npx skills add panjose/Co-Scientist --skill hypothesis-proximity-update

Clone the repo

git clone --depth 1 https://github.com/panjose/Co-Scientist

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-proximity-update/github.svg)](https://agentmods.dev/skills/panjose/co-scientist/hypothesis-proximity-update)

Your own site

<a href="https://agentmods.dev/skills/panjose/co-scientist/hypothesis-proximity-update"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-proximity-update/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/panjose/co-scientist/hypothesis-proximity-update"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-proximity-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,271 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00020	$0.01271
Opus 5	$0.00010	$0.00635
Sonnet 5	$0.00004	$0.00254
Haiku 4.5	$0.00002	$0.00127

Measured 12d ago against content hash b8f0ff6f26c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hypothesis-proximity-update 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 12d 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.

skills/hypothesis-proximity-update/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hypothesis-proximity-update

Goal:

Update hypothesis proximity state by invoking the canonical embedding bridge for one hypothesis.

Inputs:

optional existing state/PROXIMITY_GRAPH.json
target hypothesis_id
run-frozen embedding provider settings from state/RESOLVED_RUN_CONFIG.json

Outputs:

updated state/proximity_receipts/<hypothesis_id>.json
updated state/PROXIMITY_STATUS.json
updated in-memory ProximityGraphContract
updated state/PROXIMITY_GRAPH.json when the provider returns a valid embedding
updated state/PIPELINE_STATE.json
updated state/CURRENT_STAGE.json

Context Loading:

Open skills/shared-references/schema-index.md.
Read packages/agent_contracts/state.py and confirm the exact ProximityGraphContract shape before writing state/PROXIMITY_GRAPH.json.
Read packages/agent_contracts/proximity.py and confirm the proximity receipt and status schemas before interpreting provider outcomes.
Read packages/agent_contracts/pipeline_runtime.py before updating state/PIPELINE_STATE.json or state/CURRENT_STAGE.json.
Load the current proximity graph if it exists. If it does not exist yet, start from an empty ProximityGraphContract.
Treat embedding generation as a bridge/tool concern. Host agents must not generate, infer, paste, or hand-write numeric embeddings in prompt output.
Do not skip this skill merely because no embedding vector is already present in the execution context.

Execution Contract:

This skill is deterministic and must not call an LLM.
Use from tools import sync_pipeline_stage_artifacts as the canonical paired write surface for entering the Proximity substage.
On entry, call tools.sync_pipeline_stage_artifacts(run_dir, current_phase="Proximity", current_skill="hypothesis-proximity-update").
Use from tools import update_hypothesis_proximity as the stable invocation surface.
The exported bridge is implemented in packages/agent_mechanics/hypothesis_embedding.py.
The canonical hypothesis-to-embedding text formatter is implemented in packages/agent_mechanics/hypothesis_embedding_text.py.
The helper signature is update_hypothesis_proximity(run_dir, hypothesis_id, config=None, provider=None) -> ProximityEmbeddingReceiptContract.
The bridge formats the hypothesis text, reads the run-frozen proximity provider settings from state/RESOLVED_RUN_CONFIG.json unless an explicit test config is passed, calls the configured provider when enabled, records a proximity receipt/status, and updates state/PROXIMITY_GRAPH.json only when a valid embedding is returned.
Provider-specific backends such as openai_compatible and gemini must remain behind tools.update_hypothesis_proximity(...); host agents must not call provider SDKs directly or paste provider-returned vectors into artifacts.
The lower-level graph helper remains tools.update_proximity_graph(...), implemented in packages/agent_mechanics/proximity_update.py; host agents must not call it with prompt-fabricated vectors.
This skill must not hand-write embeddings, infer embeddings from hypothesis prose, or fabricate placeholder numeric vectors.
If the provider is disabled, unavailable, invalid, or fails, preserve the bridge-written receipt/status, do not fabricate a graph update, and return control to ranking with receipt-gated fallback semantics.

Execution Steps:

Open skills/shared-references/schema-index.md, then read packages/agent_contracts/state.py, packages/agent_contracts/proximity.py, and packages/agent_contracts/pipeline_runtime.py before writing proximity or run-level stage artifacts.
Before running the bridge, call tools.sync_pipeline_stage_artifacts(run_dir, current_phase="Proximity", current_skill="hypothesis-proximity-update").
Confirm the target hypothesis_id identifies an existing canonical hypotheses/<id>/HYPOTHESIS.json artifact.
Call tools.update_hypothesis_proximity(run_dir, hypothesis_id) exactly once for the target hypothesis.
Inspect the returned ProximityEmbeddingReceiptContract and the persisted state/proximity_receipts/<hypothesis_id>.json.
If the receipt status is succeeded, validate the updated state/PROXIMITY_GRAPH.json.
If the receipt status is skipped_disabled, skipped_provider_unavailable, failed_provider_error, or failed_invalid_embedding, preserve the receipt/status and return control to ranking. Do not infer or fabricate placeholder embeddings from text, IDs, or manual feature heuristics.
Validate the updated receipt/status artifacts before declaring completion.

Read the full file on GitHub · 77 lines

Changes

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.

12d ago First seen · 77 lines · 20 tokens per session scan A b8f0ff6f26c3

Subscribe to this mod's changes

hypothesis-proximity-update is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,271 once invoked, about $0.0001 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.

Claude Code Data and AI RAG and vectors Research co-scientist hypothesis-generation reproducible-research research-agent scientific-discovery

swmm-rag-memory

Retrieve relevant Agentic SWMM modeling memory from audited runs, modeling-memory summaries, and Obsidian-compatible notes at query time. Use when a user asks for RAG, similar past runs, evidence-linked memory retrieval, historical QA/failure patterns, or memory-grounded answers.

Zhonghao1995/agentic-swmm-workflow · 62 tokens

embeddings

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.

ruvnet/ruflo · 62 tokens

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens

hypothesis-proximity-update

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

hypothesis-proximity-update

What this file has done since we first saw it

Other skills, from other repositories

swmm-rag-memory

embeddings

llm-app-patterns

9router-embeddings

azure-search-documents-dotnet

evo2