agentmods.dev

convergence-check

convergence-check is a skill for Claude Code, Codex from panjose/Co-Scientist. It costs 23 tokens per session (520 once invoked), scanned A, original, Apache-2.0.

A deterministic check for whether a hypothesis has newly entered the current top-k set, meaning the selected group of highest-ranked hypotheses. It updates a convergence counter without using an AI language model.

In plain words
What is it for?
Use it inside a research evolution loop to compare previous and current leading-hypothesis sets and update convergence state.
Why use it?
It provides a consistent way to track whether research results are settling around the same leading hypotheses. It also checks the expected project-state format before updating it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 5repo 2mo ago A scan 23 tokens original Apache-2.0

Good fit Use it inside a research evolution loop to compare previous and current leading-hypothesis sets and update convergence state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panjose/co-scientist/convergence-check
View source ↗ panjose/Co-Scientist
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 convergence-check
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.

agentmods badge for convergence-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/panjose/co-scientist/convergence-check/github.svg)](https://agentmods.dev/skills/panjose/co-scientist/convergence-check)
Your own site
<a href="https://agentmods.dev/skills/panjose/co-scientist/convergence-check"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/convergence-check/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.

agentmods 80×15 button for convergence-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/panjose/co-scientist/convergence-check"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/convergence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 520 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00520
Opus 5 $0.00012 $0.00260
Sonnet 5 $0.00005 $0.00104
Haiku 4.5 $0.00002 $0.00052

Measured 9d ago against content hash 0f8c4b3ec961, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

convergence-check 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.

skills/convergence-check/SKILL.md · 56 lines

What it actually says

convergence-check

Goal:

  • Evaluate whether a hypothesis newly entered the current top-k set and update the convergence counter deterministically.

Inputs:

  • hypothesis_id
  • previous_top_k_ids
  • current_top_k_ids
  • current convergence count
  • caller-owned state/EVOLUTION_STATE.json

Outputs:

  • ConvergenceCheckResult
  • updated convergence count
  • when consumed by the evolution loop, updated state/EVOLUTION_STATE.json

Context Loading:

  • Open skills/shared-references/schema-index.md.
  • Read packages/agent_contracts/pipeline_control.py and confirm the exact EvolutionStateContract shape before writing state/EVOLUTION_STATE.json.
  • Treat the top-k sets as caller-supplied frontier inputs. This skill only evaluates the rule and updates the counter.

Execution Contract:

  • This skill is deterministic and must not call an LLM.
  • Use from tools import evaluate_convergence as the stable invocation surface.
  • The exported helper is implemented in packages/agent_mechanics/convergence_check.py.
  • The helper signature is evaluate_convergence(hypothesis_id, previous_top_k_ids, current_top_k_ids, current_convergence_count) -> ConvergenceCheckResult.

Execution Steps:

  1. Open skills/shared-references/schema-index.md, then read packages/agent_contracts/pipeline_control.py before writing state/EVOLUTION_STATE.json.
  2. Read the candidate hypothesis_id, the previous and current top-k sets, and the current convergence count.
  3. Call tools.evaluate_convergence(hypothesis_id, previous_top_k_ids, current_top_k_ids, current_convergence_count).
  4. Return the ConvergenceCheckResult to the caller.
  5. When used by the evolution loop, persist the returned entered_top_k and convergenceCount values into state/EVOLUTION_STATE.json.
  6. Validate any updated state/EVOLUTION_STATE.json artifact before declaring completion.

Artifact Rules:

  • The convergence rule is fixed: entering the top-k frontier resets the counter to zero; otherwise the counter increments by one.
  • Do not fold additional stopping logic into this skill. Stop decisions belong to evolution state management and completion verification.

Completion Rule:

  • This skill is complete only when the deterministic result has been produced and any caller-owned state/EVOLUTION_STATE.json update matches that result exactly.
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.

  1. 9d ago First seen · 56 lines · 23 tokens per session scan A 0f8c4b3ec961

Subscribe to this mod's changes

convergence-check is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 520 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 CodeResearchco-scientisthypothesis-generationreproducible-researchresearch-agentscientific-discovery
Related

Other skills, from other repositories

figure-style

Publication-grade correctness and legibility rules for final-deliverable scientific figures, not exploratory plots. Use for a figure that will ship in a report, paper, export, or kept artifact. Covers data fidelity, label economy, color threading, chart choice, layout, and render-then-verify QA without imposing a…

aipoch/open-science · 91 tokens

remote-compute-ssh

Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.

aipoch/open-science · 53 tokens

scvi-tools

Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…

aipoch/open-science · 100 tokens

literature-review

Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.

aipoch/open-science · 54 tokens

openfold3

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.

aipoch/open-science · 60 tokens

self-awareness

Inspect Open Science's JavaScript control REPL, discover managed Project files, Sessions, and Agent Frames, and safely feature-gate host. calls with host.capabilities(). Use when an Agent needs to discover available host APIs, locate an Artifact or Upload Version, diagnose a Session, or read a Frame transcript in the…

aipoch/open-science · 69 tokens