evidence-curator

evidence-curator is a skill for Claude Code from Biolytics-AI/rhetoric-engine. It costs 38 tokens per session (753 once invoked), scanned A, original, MIT.

A research-evidence organiser that connects each claim to supporting sources. It records which evidence is primary or backup, where it came from, how reliable it is, and what proof is missing.

In plain words
What is it for?
Use it to build a claim-and-evidence table, select proof for individual slides, record source details, prepare backup evidence, and identify evidence gaps.
Why use it?
It prevents presentations from relying on unsupported, weak, outdated, or disputed claims. It also makes sources and caveats easier to review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rhetoric-engine plugin — 12 skills shipped together

Good fit Use it to build a claim-and-evidence table, select proof for individual slides, record source details, prepare backup evidence, and identify evidence gaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/biolytics-ai/rhetoric-engine/evidence-curator
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 Biolytics-AI/rhetoric-engine --skill evidence-curator
Clone the repo
git clone --depth 1 https://github.com/Biolytics-AI/rhetoric-engine

Made for: Claude Code.

Or install rhetoric-engine, the plugin that ships this one along with the rest of its 12 skills.

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 evidence-curator

README.md
[![agentmods](https://agentmods.dev/badge/skills/biolytics-ai/rhetoric-engine/evidence-curator/github.svg)](https://agentmods.dev/skills/biolytics-ai/rhetoric-engine/evidence-curator)
Your own site
<a href="https://agentmods.dev/skills/biolytics-ai/rhetoric-engine/evidence-curator"><img src="https://agentmods.dev/badge/skills/biolytics-ai/rhetoric-engine/evidence-curator/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 evidence-curator

Your own site · 80×15
<a href="https://agentmods.dev/skills/biolytics-ai/rhetoric-engine/evidence-curator"><img src="https://agentmods.dev/badge/skills/biolytics-ai/rhetoric-engine/evidence-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 753 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 $0.00038 $0.00753
Opus 5 $0.00019 $0.00377
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00075

Measured 10d ago against content hash 3561b8bd2b8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

evidence-curator 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 10d 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/evidence-curator/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidence Curator

Curate proof so every claim has credible, audience-legible support. Separate primary evidence, backup evidence, provenance, and gaps.

Inputs

  • Approved intent brief, insight artifact, argument spine, and slide thesis map.
  • Available sources, data, research, examples, quotations, user notes, and constraints.
  • Audience trust standards, domain norms, objections, and source restrictions.
  • Visual reasoning or cognitive design notes when evidence must support a specific slide treatment.

Outputs

Return an Evidence Dossier with:

  • claim_evidence_matrix: each claim, required proof job, available evidence, strength, caveats, and source.
  • per_slide_evidence_choice: primary evidence selected for each slide thesis and why.
  • source_provenance_notes: origin, date, author, method, reliability, permissions, and citation needs.
  • backup_evidence: secondary proof for likely objections, appendix use, or Q&A.
  • evidence_gaps: missing, weak, stale, disputed, or unsupported claims that need sourcing or revision.

Workflow

  1. List every claim from the argument spine and slide thesis map.
  2. Define the proof job for each claim: establish fact, quantify scale, compare options, show trend, validate cause, demonstrate example, or answer objection.
  3. Match available evidence to claims and reject evidence that is merely interesting.
  4. Rank evidence by relevance, credibility, recency, specificity, audience legibility, and resistance to challenge.
  5. Choose one primary evidence item per slide where possible and assign backup evidence for likely objections.
  6. Record provenance, caveats, permissions, and citation requirements.
  7. Flag evidence gaps and recommend whether to source more, weaken the claim, move material to backup, or ask the user.

Evaluation Checks

  • Every important claim has evidence or an explicit gap.
  • Primary evidence directly supports the slide thesis.
  • Backup evidence prepares for objections without overloading the main flow.
  • Source provenance is sufficient for review and citation.
  • Weak, decorative, or irrelevant evidence is rejected.
  • Evidence choices do not create new claims beyond the approved argument.

Read the full file on GitHub · 66 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. 10d ago First seen · 66 lines · 38 tokens per session scan A 3561b8bd2b8c

Subscribe to this mod's changes

evidence-curator is a skill published in the GitHub repository Biolytics-AI/rhetoric-engine (1 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 753 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

mongodb-query-optimizer

Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…

fcakyon/claude-codex-settings · 98 tokens

polar-local-environment

This skill should be used when setting up or managing Polar local development environment with Docker.

fcakyon/claude-codex-settings · 22 tokens

neo4j-modeling-skill

Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…

neo4j-contrib/neo4j-skills · 152 tokens

lov-article-creator

A skill that turns source material or a draft into a complete, branded WeChat public-account article package.

lovstudio/skills · 75 tokens

lov-repo2docs

Turn any folder of source material — a code repository, a pile of articles, a mixed knowledge dump with images — into a professional, polished Fumadocs (Next.js) documentation website, then deploy it to https://{product-id}.example.com/docs. Works by reading the folder one unit at a time and incrementally growing and…

lovstudio/skills · 186 tokens