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 EvoClaw/amplify --skill claim-evidence-alignmentgit clone --depth 1 https://github.com/EvoClaw/amplifyWrote 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/evoclaw/amplify/claim-evidence-alignment)<a href="https://agentmods.dev/skills/evoclaw/amplify/claim-evidence-alignment"><img src="https://agentmods.dev/badge/skills/evoclaw/amplify/claim-evidence-alignment.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00609 |
| Opus 5 | $0.00016 | $0.00304 |
| Sonnet 5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
claim-evidence-alignment 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claim-Evidence Alignment (Discipline Layer)
Overview
A claim without evidence is an opinion, not a result. This skill activates at Phase 5 (results integration) and remains in effect through Phase 6 (paper writing).
Core principle: Evidence first, claim second. Never the reverse.
Violating the letter of this rule is violating the spirit of this rule.
The Iron Law
EVERY CLAIM MUST MAP TO SPECIFIC EVIDENCE. UNMAPPED CLAIMS ARE DELETED.
The Claim-Evidence Mapping Table
Before writing any paper section, build and maintain this table:
| Claim | Evidence Source | Figure/Table | Statistical Support |
|---|---|---|---|
| (exact claim text) | (experiment, dataset, condition) | (Fig X / Table Y) | (test, p-value, CI) |
Every row must be complete. Empty cells mean the claim is not ready to write.
When This Runs
- Before paper writing begins (G4 gate): Full table must exist and pass review.
- After each paper section is drafted: Re-check that no new unmapped claims crept in.
Rules
- Every claim intended for the paper must link to a specific figure, table, experiment, or statistical test.
- Claims with insufficient evidence must be either: (a) deleted, or (b) supported by running additional experiments. No third option.
- Claims with weak evidence (e.g., p=0.08) must use weakened language — "suggests" not "demonstrates", "indicates" not "proves".
- The methodology-reviewer agent checks claim-evidence alignment independently. Passing your own check is necessary but not sufficient.
Red Flags — STOP
- Claim not linked to any figure or table
- Statistical test not reported for a comparison claim
- Using "significantly" without a significance test
- Evidence column says "see results" instead of a specific reference
- Claim language stronger than the statistical support warrants
Rationalization Prevention
| Excuse | Reality |
|---|---|
| "The trend is clear visually" | Visual trends need statistical backing. Show the numbers. |
| "Everyone knows this is true" | Common knowledge still needs citation. Your claim needs evidence. |
| "The result is obvious from the method" | Theoretical arguments need empirical validation in a paper. |
| "I'll add the evidence later" | No claim without evidence. Write evidence first, claim second. |
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.
- 8d ago First seen · 70 lines · 33 tokens per session scan A d30bed7f8fbd
claim-evidence-alignment is a skill published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 609 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 2026-08-30.
Other skills, from other repositories
paper2poster
Convert academic papers (PDF) into conference posters (HTML/PNG). You are the conductor: you decide what each section needs — an original paper figure or text — write the outline, hand-author the poster HTML, and iterate on the render using your own visual read and a blind-reader content quiz. Use when the user wants…
paper2slides
Turn an academic paper PDF into a presentation deck (.pptx) end-to-end. Use this skill whenever the user wants to "make slides from a paper", "generate a deck from this PDF", "make a PPT from this paper", "generate slides from a PDF document", "make a deck from a research paper", or supplies a research paper PDF and…
5writing
A paper-writing workflow for mathematical modelling competitions, supporting both Typst and LaTeX. It uses analysis, results, figures, and a competition template to assemble the document.
6verity
A final-checking workflow for mathematical modelling competition papers, using either Typst or LaTeX to build the document. It checks the finished paper and its supporting files before submission.
1start-mathmodel
A starting workflow for mathematical-modeling competitions, which are contests where teams use mathematics, data, and code to solve real-world problems. It asks for preferences, creates planning files, and coordinates later analysis, modeling, coding, charting, diagram, writing, and verification stages.
4drawio
A diagram-making stage for mathematical-modeling projects. It uses existing analysis and results reports to create technical route maps, solution flowcharts, model diagrams, and data-processing diagrams in Drawio, a tool for creating structured diagrams, then exports them as PDF files.