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 run-policy-routergit 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/run-policy-router)<a href="https://agentmods.dev/skills/panjose/co-scientist/run-policy-router"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/run-policy-router/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/run-policy-router"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/run-policy-router.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 | $0.00027 | $0.00447 |
| Opus 5 | $0.00014 | $0.00224 |
| Sonnet 5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
run-policy-router 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 11d 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
run-policy-router
Goal:
- Interpret the user's high-level research intent into
RUN_POLICY.yamlandstate/POLICY_DECISION.json.
Inputs:
- one run directory root
- run-local
input.md - optional
RUN_POLICY.yaml - research brief and operator constraints
Outputs:
- updated
RUN_POLICY.yaml - updated
state/POLICY_DECISION.json
Context Loading:
- Open
skills/shared-references/schema-index.md. - Read
packages/agent_contracts/policy.pyand confirm the exactRunPolicyContractplusPolicyDecisionContractshapes before writingRUN_POLICY.yamlorstate/POLICY_DECISION.json. - Read
input.mdplus any operator constraints that should influence the high-level routing axes.
Execution Contract:
- The router must stay at the high-level policy layer and must not invent raw numeric mechanics values directly.
- Allowed routing axes are documented in
../shared-references/policy-contract.md. - Downstream numeric settings are resolved separately into
state/RESOLVED_RUN_CONFIG.json. - This skill owns canonical policy artifact emission only:
RUN_POLICY.yamlstate/POLICY_DECISION.json
- This skill does not own numeric mechanics resolution, direct strategy routing, or downstream evolution-state writes.
Execution Steps:
- Open
skills/shared-references/schema-index.md, then readpackages/agent_contracts/policy.pybefore writingRUN_POLICY.yamlorstate/POLICY_DECISION.json. - Interpret the research brief into the allowed policy axes only.
- Write canonical
RUN_POLICY.yamlandstate/POLICY_DECISION.json. - Do not invent raw numeric mechanics values that belong in
state/RESOLVED_RUN_CONFIG.json. - Validate the emitted policy artifacts.
Completion Rule:
- This skill is complete only when
RUN_POLICY.yamlandstate/POLICY_DECISION.jsonhave been written in canonical form and remain consistent with the selected high-level policy axes.
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.
- 11d ago First seen · 51 lines · 27 tokens per session scan A d73b1234c447
run-policy-router is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 447 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.