agentmods.dev

hypothesis-review-pipeline

hypothesis-review-pipeline is a skill for Claude Code, Codex from panjose/Co-Scientist. It costs 26 tokens per session (1,567 once invoked), scanned A, original, Apache-2.0.

A staged review process for testing one research hypothesis and saving each review stage as structured files. A hypothesis is a specific claim that can be checked against evidence or observation.

In plain words
What is it for?
Use it for initial, full, deep-verification, observation, and simulation reviews, including literature searches when outside research evidence is needed.
Why use it?
It keeps research reviews organized, resumable, and separate by stage instead of combining all reasoning into one informal assessment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Codex.

not rated 5repo 3mo ago A scan 26 tokens original Apache-2.0

Good fit Use it for initial, full, deep-verification, observation, and simulation reviews, including literature searches when outside research evidence is needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panjose/co-scientist/hypothesis-review-pipeline
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 hypothesis-review-pipeline
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 hypothesis-review-pipeline

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/panjose/co-scientist/hypothesis-review-pipeline"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/hypothesis-review-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,567 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 $0.00026 $0.01567
Opus 5 $0.00013 $0.00783
Sonnet 5 $0.00005 $0.00313
Haiku 4.5 $0.00003 $0.00157

Measured 12d ago against content hash 3ba08841ee41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hypothesis-review-pipeline 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-review-pipeline/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hypothesis-review-pipeline

Goal:

  • Run the decomposed review pipeline for a single hypothesis and persist each review stage as a structured artifact.

Inputs:

  • ResearchPlan
  • MetaReview
  • Hypothesis
  • optional resume context from state/PIPELINE_STATE.json

Outputs:

  • hypotheses/<id>/REVIEW/INITIAL_REVIEW.json
  • hypotheses/<id>/REVIEW/FULL_REVIEW.json
  • hypotheses/<id>/REVIEW/DEEP_VERIFICATION.json
  • hypotheses/<id>/REVIEW/OBSERVATION_REVIEW.json
  • hypotheses/<id>/REVIEW/SIMULATION_REVIEW.json
  • hypotheses/<id>/REVIEW/REVIEW_SUMMARY.json
  • literature/queries/<query_id>/* when full review or deep verification needs external literature evidence
  • updated hypotheses/<id>/HYPOTHESIS.json
  • updated state/PIPELINE_STATE.json
  • updated state/CURRENT_STAGE.json

Sub-skills:

  • hypothesis-initial-review
  • literature-search
  • hypothesis-full-review
  • hypothesis-deep-verification
  • hypothesis-observation-review
  • hypothesis-simulation-review
  • hypothesis-review-summary

Context Loading:

  • Open skills/shared-references/schema-index.md.
  • Read packages/agent_contracts/review.py before writing any per-stage review artifact under hypotheses/<id>/REVIEW/.
  • Read packages/agent_contracts/hypothesis.py before updating the embedded review payload inside hypotheses/<id>/HYPOTHESIS.json.
  • Read packages/agent_contracts/literature.py and skills/shared-references/literature-search-contract.md before dispatching hypothesis-full-review or hypothesis-deep-verification.
  • Read packages/agent_contracts/pipeline_runtime.py before updating state/PIPELINE_STATE.json or state/CURRENT_STAGE.json.
  • Read skills/shared-references/codex-reviewer-routing.md before using any optional Codex reviewer subagent route.
  • Read RUN_POLICY.yaml before dispatching review work so the active review_rigor setting is honored.
  • Read the current hypothesis, research plan, and any optional run-level review guidance before starting the stage sequence.

Execution Contract:

  • This pipeline skill does not own hidden prompt templates.
  • It orchestrates atomic review skills so the runtime can trace each review stage independently.
  • Downstream atomic review skills remain responsible for the exact field-level contents of each standalone review artifact.
  • The canonical hypotheses/<id>/HYPOTHESIS.json artifact must be updated after every review stage so the embedded review payload stays in sync with the per-stage review files.
  • Use from tools import sync_hypothesis_review after each stage artifact write. The canonical synchronization helper is implemented in packages/run_artifacts/review_sync.py; do not hand-edit embedded review JSON.
  • Use from tools import sync_pipeline_stage_artifacts as the canonical paired write surface for entering the Reflection substage.
  • Treat tools.sync_hypothesis_review(run_dir, hypothesis_id) as a hard gate. If it fails, stop the review sequence immediately instead of continuing with later stages.
  • On entry, call tools.sync_pipeline_stage_artifacts(run_dir, current_phase="Reflection", current_skill="hypothesis-review-pipeline") before starting the review sequence.
  • When consumed by a host agent, validate both the embedded hypothesis review payload and the per-stage review artifacts. If validation fails, stop and repair the review bundle before running the next stage or returning control.
  • Full review and deep verification must use tools.search_literature(run_dir, request) or an existing matching EvidenceBundleContract before making external literature support claims.
  • The review pipeline must not accept prompt-invented paper metadata or model-memory citations as formal evidence.
  • The review pipeline must not accept empty completed review artifacts. A completed or passing stage must contain concrete, hypothesis-specific findings that downstream evolution and ranking can use.
  • Do not use placeholder review phrases such as Viable evolved hypothesis, Refined from parent, Must outperform parent, Synthesize evolved catalyst, or Benchmark against parent as the substantive content of any completed review artifact.
  • Codex reviewer subagents are optional. If unavailable, run the same review contract in the main thread and record reviewerRoute = local_main_thread in the trace.
  • If a Codex reviewer subagent is used, record state/agent_traces/codex/<skill>/<timestamp>.json; the trace is audit evidence and must not replace canonical review artifacts.
  • Reviewer subagents must not write deterministic mechanics artifacts or bypass tools.sync_hypothesis_review and schema validation.
  • Regardless of review_rigor, run the full review stack for every hypothesis:
    • hypothesis-full-review
    • hypothesis-deep-verification
    • hypothesis-observation-review
    • hypothesis-simulation-review
  • review_rigor may shorten or deepen the reasoning inside those stages, but it must not disable any review artifact.

Read the full file on GitHub · 93 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.

  1. 12d ago First seen · 93 lines · 26 tokens per session scan A 3ba08841ee41

Subscribe to this mod's changes

hypothesis-review-pipeline is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,567 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 CodeResearchWriting and docsco-scientisthypothesis-generationreproducible-researchresearch-agentscientific-discovery
Related

Other skills, from other repositories

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

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

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