evidence-calibration-review

evidence-calibration-review is a skill for Claude Code from Avyayalaya/agent-council. It costs 129 tokens per session (3,965 once invoked), scanned A, original, MIT.

A review that checks each important claim in a document against the strength of its supporting evidence.

In plain words
What is it for?
Use it to check analyses, memos, public pitches, and other documents containing many factual claims.
Why use it?
It catches claims stated too confidently without strong proof, as well as well-supported claims presented too cautiously. It also flags sources used only for appearance and collections of anecdotes treated as proof.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Codex.

Part of the agent-council plugin — 5 skills, 2 commands, 1 MCP server shipped together

Good fit Use it to check analyses, memos, public pitches, and other documents containing many factual claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avyayalaya/agent-council/evidence-calibration-review
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 Avyayalaya/agent-council --skill evidence-calibration-review
Clone the repo
git clone --depth 1 https://github.com/Avyayalaya/agent-council

Made for: Claude Code.

Or install agent-council, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 1 MCP server.

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-calibration-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/avyayalaya/agent-council/evidence-calibration-review/github.svg)](https://agentmods.dev/skills/avyayalaya/agent-council/evidence-calibration-review)
Your own site
<a href="https://agentmods.dev/skills/avyayalaya/agent-council/evidence-calibration-review"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-council/evidence-calibration-review/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-calibration-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/avyayalaya/agent-council/evidence-calibration-review"><img src="https://agentmods.dev/badge/skills/avyayalaya/agent-council/evidence-calibration-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,965 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 $0.00129 $0.03965
Opus 5 $0.00064 $0.01982
Sonnet 5 $0.00026 $0.00793
Haiku 4.5 $0.00013 $0.00396

Measured 12d ago against content hash ed5dab580a87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

evidence-calibration-review 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/evidence-calibration-review/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Run a per-claim evidence-tier audit on a text artifact before it ships. The Evidence & Calibration role reads the artifact claim by claim and asks one question per claim: what tier of evidence supports it, and is the artifact's stated confidence consistent with that tier?

A claim asserted with high confidence on Tier 6 (inferred) evidence is a calibration failure. A claim hedged with "perhaps" when the evidence is Tier 1 (primary source, verified) is also a calibration failure — under-claiming is its own honesty failure. The skill catches both directions.

This is the boring and the load-bearing role on the panel. "Where is the source for X?" is the question that ends careers. Evidence & Calibration surfaces every unsourced claim before it ships.

The skill encodes the Evidence & Calibration role from the agent-council 5-deliberator quality gate. Use standalone for fast evidence audit, or compose with the other 4 deliberator skills for fuller coverage.

When to Use / When NOT to Use

Use this skill when:

  • A claim-dense artifact (analysis, memo, public pitch) is about to ship and you want every load-bearing claim tiered
  • You suspect over-claiming (high confidence on weak evidence) or under-claiming (hedging what is actually verified) and want both directions surfaced
  • A piece relies on attributions ("X said Y" / "Microsoft did Z") and you want each verified or hedged appropriately
  • You need to catch P11 (citation-as-decoration), P17 (pile-of-anecdotes-as-evidence), or P54 (unverifiable-single-source) patterns explicitly
  • You are running a multi-deliberator review and need the Evidence & Calibration seat filled

Do NOT use this skill when:

  • You need a structural critique (load-bearing claims, counter-positions) — use skeptic-review instead
  • You need a voice critique (banned patterns, register check, CXO test) — use voice-identity-review instead
  • You need a strategic-fit check (goal alignment, opportunity cost) — use strategy-stakes-review instead
  • The artifact has no factual claims (a pure brainstorming note or speculative framing)
  • You want the operator's own source-finding work done for them — this skill names the gap; the operator either finds the source or weakens the claim

Read the full file on GitHub · 259 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 · 259 lines · 129 tokens per session scan A ed5dab580a87

Subscribe to this mod's changes

evidence-calibration-review is a skill published in the GitHub repository Avyayalaya/agent-council (10 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 3,965 once invoked, about $0.0006 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.