agentmods.dev

literature-search

literature-search is a skill for Claude Code, Codex from panjose/Co-Scientist. It costs 21 tokens per session (698 once invoked), scanned A, original, Apache-2.0.

A literature-search workflow that sends one evidence query through a standard search bridge and saves traceable paper and search records.

In plain words
What is it for?
Use it to run an evidence search and produce structured JSON, a Markdown evidence bundle, a search trace, and related literature records.
Why use it?
It keeps search requests, provider responses, candidate papers, verified papers, and supporting evidence together so results can be checked later.

Skill for Claude CodeCodex

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

not rated 5repo 3mo ago A scan 21 tokens original Apache-2.0

Good fit Use it to run an evidence search and produce structured JSON, a Markdown evidence bundle, a search trace, and related literature records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panjose/co-scientist/literature-search
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 literature-search
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 literature-search

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/panjose/co-scientist/literature-search"><img src="https://agentmods.dev/badge/skills/panjose/co-scientist/literature-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 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 $0.00021 $0.00698
Opus 5 $0.00010 $0.00349
Sonnet 5 $0.00004 $0.00140
Haiku 4.5 $0.00002 $0.00070

Measured 11d ago against content hash c7713a00510e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

literature-search 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.

skills/literature-search/SKILL.md · 60 lines

What it actually says

Goal:

  • Run the canonical literature search bridge for one evidence query and persist traceable evidence artifacts.

Inputs:

  • active run directory
  • a SearchRequestContract payload or enough context to build one
  • optional existing literature/queries/<query_id>/REQUEST.json

Outputs:

  • literature/queries/<query_id>/REQUEST.json
  • literature/queries/<query_id>/PROVIDER_RECEIPTS.json
  • literature/queries/<query_id>/CANDIDATE_PAPERS.json
  • literature/queries/<query_id>/VERIFIED_PAPERS.json
  • literature/queries/<query_id>/EVIDENCE_BUNDLE.json
  • literature/queries/<query_id>/EVIDENCE_BUNDLE.md
  • literature/queries/<query_id>/SEARCH_TRACE.jsonl
  • literature/bundles/<bundle_id>.json

Context Loading:

  • Open skills/shared-references/schema-index.md.
  • Open skills/shared-references/literature-search-contract.md.
  • Read packages/agent_contracts/literature.py before building or editing a search request or evidence bundle.
  • Read tools/literature_search_client.py before invoking the bridge.

Execution Contract:

  • Import and call from tools import search_literature.
  • When the host exposes the configured co_scientist_search_bridge MCP server, its tools are an allowed transport for the same canonical bridge.
  • If the MCP server is unavailable, fall back to the Python tools surface instead of performing informal web search.
  • Do not perform informal web search as a substitute for tools.search_literature(...).
  • Do not invent papers, DOIs, arXiv IDs, venues, citation counts, or abstracts.
  • Preserve provider failure receipts. A failed provider is evidence about retrieval coverage and must not be hidden.
  • If retrieval_metadata.status is blocked, return that blocked state to the caller instead of fabricating an evidence bundle.
  • If retrieval_metadata.status is partial, downstream callers may continue only when they preserve the partial-source limitation.

Execution Steps:

  1. Open skills/shared-references/schema-index.md, skills/shared-references/literature-search-contract.md, and packages/agent_contracts/literature.py.
  2. Build a SearchRequestContract with a stable query_id, goal, query, query_type, providers, filters, and consumer.
  3. Call tools.search_literature(run_dir, request) through the stable tools surface, or call the equivalent configured MCP search bridge tool when it is available.
  4. Read the returned EvidenceBundleContract and confirm the run-local artifacts were written.
  5. If the bundle status is blocked, stop and report the blocked retrieval state to the caller.
  6. If the bundle status is partial or succeeded, return the bundle_id and query_id to the caller.
  7. Run python -m tools.validation.contract_validation <run_dir> --skill literature-search.

Completion Rule:

  • This skill is complete only when the search bridge has written a canonical evidence bundle or an auditable blocked retrieval state, and the literature artifacts validate.
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. 11d ago First seen · 60 lines · 21 tokens per session scan A c7713a00510e

Subscribe to this mod's changes

literature-search is a skill published in the GitHub repository panjose/Co-Scientist (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 698 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 CodeResearchScientificco-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

paper-narrative

Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a grounded brief from the manuscript and captions, review the full deck as a handling editor, and hand an ordered figure arc to figure-composer.

aipoch/open-science · 58 tokens

esmfold2

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…

aipoch/open-science · 223 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

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