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 panjose/Co-Scientist --skill hypothesis-evolve-coherencegit clone --depth 1 https://github.com/panjose/Co-ScientistWrote 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/panjose/co-scientist/hypothesis-evolve-coherence)<a href="https://agentmods.dev/skills/panjose/co-scientist/hypothesis-evolve-coherence"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-evolve-coherence/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/panjose/co-scientist/hypothesis-evolve-coherence"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-evolve-coherence.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.00673 |
| Opus 5 | $0.00012 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
hypothesis-evolve-coherence 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.
What it actually says
hypothesis-evolve-coherence
Goal:
- Generate exactly one child hypothesis that improves logical coherence, causal consistency, and assumption hygiene.
Inputs:
research_plan/RESEARCH_PLAN.json- selected parent
hypotheses/<id>/HYPOTHESIS.jsonartifacts - parent review artifacts
- active
state/STRATEGY_PLAN.json
Outputs:
hypotheses/<id>/HYPOTHESIS.jsonhypotheses/<id>/HYPOTHESIS.mdhypotheses/<id>/ORIGIN.json
Context Loading:
- Open
skills/shared-references/schema-index.md. - Read
packages/agent_contracts/hypothesis.pyand confirm the exactHypothesisContractshape before writinghypotheses/<id>/HYPOTHESIS.json. - Read
research_plan/RESEARCH_PLAN.json. - Read
state/STRATEGY_PLAN.json. - Read each selected parent hypothesis and its review bundle.
- Confirm that the round selected
coherence_evolution.
Execution Prompt Contract:
- System Intent:
- You are repairing contradictions, invalid assumptions, and causal gaps in the parent hypothesis.
- Required Reasoning Focus:
- Remove internal contradictions first.
- Tighten the causal chain so each step is explicit and testable.
- Preserve novelty while reducing logical fragility.
- Do Not Do:
- Do not add unrelated speculative branches.
- Do not emit multiple candidate repairs.
- Quality Floor:
- The child must directly address at least one specific weakness from the parent review bundle.
origin.content.statementmust name concrete materials, catalysts, reaction conditions, mechanistic variables, or experimental targets from the parent and research goal.origin.content.mechanismmust explain a causal chain; do not write only generic phrases such asimproved mechanism,targeted improvement, orreview-identified weaknesses.origin.content.experimental_designmust include 3-6 numbered steps with measurable readouts, controls, or decision thresholds.- Do not use generic refinement placeholder steps such as
Apply targeted improvement,Characterize with standard techniques,Benchmark against parent, orValidate improvement quantitatively. - If the research plan, parent hypothesis, or parent review bundle is missing, stop and report the missing artifact instead of guessing.
- Output Shape:
- Emit the canonical
HypothesisContract. origin.strategy:coherence_evolution- Populate the full nested content block, including non-empty
summaryandcategory.
- Emit the canonical
Execution Steps:
- Open
skills/shared-references/schema-index.md, then readpackages/agent_contracts/hypothesis.pybefore writinghypotheses/<id>/HYPOTHESIS.json. - Identify the coherence failures in the parent set.
- Produce exactly one corrected child hypothesis.
- Persist canonical
HYPOTHESIS.json,HYPOTHESIS.md, andORIGIN.json. - Validate the emitted hypothesis artifact.
Completion Rule:
- This skill is complete only when one logically improved child hypothesis has been written in canonical form.
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 · 68 lines · 24 tokens per session scan A 603d3e564934
hypothesis-evolve-coherence is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 673 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.
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…
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.
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…
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.
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.
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…