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 insights-from-reviewsgit 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/insights-from-reviews)<a href="https://agentmods.dev/skills/panjose/co-scientist/insights-from-reviews"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/insights-from-reviews/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/insights-from-reviews"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/insights-from-reviews.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 | $0.00018 | $0.00711 |
| Opus 5 | $0.00009 | $0.00356 |
| Sonnet 5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
insights-from-reviews 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.
What it actually says
insights-from-reviews
Goal:
- Extract recurring critique patterns from the completed review of a hypothesis.
Inputs:
research_plan/RESEARCH_PLAN.jsonhypotheses/<id>/HYPOTHESIS.json- existing
meta/INSIGHTS_FROM_REVIEWS.jsonwhen present
Outputs:
meta/INSIGHTS_FROM_REVIEWS.json- updated
state/PIPELINE_STATE.json - updated
state/CURRENT_STAGE.json
Context Loading:
- Open
skills/shared-references/schema-index.md. - Read
packages/agent_contracts/meta_review.pybefore writingmeta/INSIGHTS_FROM_REVIEWS.json. - Read
packages/agent_contracts/pipeline_runtime.pybefore updatingstate/PIPELINE_STATE.jsonorstate/CURRENT_STAGE.json. - Read
research_plan/RESEARCH_PLAN.jsonfor the active goal and evaluation boundaries. - Read the current hypothesis together with its completed review stack.
- If
meta/INSIGHTS_FROM_REVIEWS.jsonalready exists, treat it as the current accumulated insight set that must be revised rather than appended to blindly.
Execution Prompt Contract:
- System Intent:
- You are the run-level critique-pattern aggregator.
- Required Reasoning Focus:
- Compare the current hypothesis review against existing accumulated insights.
- Keep, strengthen, refine, merge, split, or remove insight statements based on the new evidence.
- Maintain a complete self-contained insight list rather than incremental append-only notes.
- Prefer concise, actionable critique patterns over vague thematic summaries.
- Do Not Do:
- Do not output only the delta from the previous insight set.
- Do not preserve unsupported or redundant insights just because they already exist.
- Do not turn one hypothesis review into a run-level generalization without enough evidence.
- Output Shape:
- Produce the exact
InsightsFromReviewsContractfrompackages/agent_contracts/meta_review.py. - When consumed inside the run pipeline, use
from tools import sync_pipeline_stage_artifactssocurrentPhase = Insights from Reviews,currentSkill = insights-from-reviews, andstageTrailstay aligned across both state artifacts. - Keep each insight short and actionable.
- Produce the exact
Execution Steps:
- Open
skills/shared-references/schema-index.md, then readpackages/agent_contracts/meta_review.pyandpackages/agent_contracts/pipeline_runtime.pybefore writingmeta/INSIGHTS_FROM_REVIEWS.jsonor updating run-level stage artifacts. - Before aggregating the new insight set, call
tools.sync_pipeline_stage_artifacts(run_dir, current_phase="Insights from Reviews", current_skill="insights-from-reviews"). - Read the research plan, current hypothesis, and its completed review artifacts.
- Read prior insights if they exist.
- Compare the new review evidence against the prior insight set.
- Produce a revised complete insight list.
- Write
meta/INSIGHTS_FROM_REVIEWS.json. - Validate before declaring completion.
Artifact Rules:
INSIGHTS_FROM_REVIEWS.jsonmust contain a complete revised insight set, not an append-only patch.- The artifact should stay concise enough to guide later stages without becoming a second full review archive.
Completion Rule:
- This skill is complete only when
meta/INSIGHTS_FROM_REVIEWS.jsonexists and is valid for downstream consumption.
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 · 70 lines · 18 tokens per session scan A 6c6d2d150af1
insights-from-reviews is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 711 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.
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.
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…
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…
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.