A note-review tool that checks the quality of notes and whether their claims match their cited sources.

Use it to review one note, a group of notes, or notes on a topic, then produce a report and repair plan.

It helps catch weak structure, duplicate notes, broken references, and claims that sources do not support.

verify — Skill for Claude Code by robinslange/learning-loop

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add robinslange/learning-loop

Claude Code

/plugin install learning-loop

Made for: Claude Code.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 7 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/robinslange/learning-loop/verify/github.svg)](https://agentmods.dev/skills/robinslange/learning-loop/verify)

Your own site

<a href="https://agentmods.dev/skills/robinslange/learning-loop/verify"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/verify/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/robinslange/learning-loop/verify"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,540 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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.04540
Opus 5.5	$0.00021	$0.01816
Sonnet 5.5	$0.00010	$0.00908
Haiku 4.5	$0.00005	$0.00454

Measured 1mo ago against content hash 90e62e3e2ce5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify 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 1mo 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.

plugin/skills/verify/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify: Note Quality and Source Integrity

Overview

Assesses vault notes on two dimensions: structural quality (depth, sourcing, linking, voice, atomicity) and source truthfulness (are URLs real, do claims match citations). Produces a combined report and fix plan that feeds into /deepen.

When to Use

/verify "note-name": single note
/verify inbox: everything in 0-inbox/
/verify fleeting: everything in 1-fleeting/ (the gate-demoted notes — catches stuck verification markers and source: unverified notes that have no other resurfacing path)
/verify permanent: everything in 3-permanent/
/verify "topic": all notes matching a topic
/verify: defaults to 0-inbox/
After a burst of captures to check what landed well
Before promoting notes from inbox to permanent
When deciding where to invest /deepen effort
When you suspect fabricated or stale references

Provenance

This skill emits provenance events for pipeline observability.

At session start (after scope identified):

ll-run provenance-emit.js '{"agent":"verify","skill":"verify","action":"session-start","intent_kind":"scope","config":{"note_count":N}}'

After scoring and verification, emit each finding via provenance-emit.js:

For each note with issues, pass the prose with --text so you never escape it into the JSON. Quotes, backticks and $ in the finding are safe as-is:

ll-run provenance-emit.js '{"agent":"verify","skill":"verify","action":"score","target":"note-filename.md","result":"fail","finding_type":"overclaim","trigger":"verify-manual","confidence":"clear","ambiguous_alt":""}' \
  --text finding_detail 'single RCT stated as consensus'

Where:

finding_type is one of: url-fabrication, author-swap, number-reassignment, overclaim, source-missing, stale, logical-gap, conflation. See agents-shared/capture-rules.md → Finding-Type Discriminator for the source-missing vs logical-gap boundary rule.
trigger is one of: verify-auto (URL/source check), verify-manual (human review), cross-note (pattern across notes), retrieval (found during search), stale-scan (date check)
confidence is clear (obvious classification) or ambiguous (could be another type)
ambiguous_alt is the alternative type considered when confidence is ambiguous, empty string when clear

Read the full file on GitHub · 316 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.

1mo ago Changed 90e62e3e2ce5
1mo ago Changed · -1 lines e156ca3f58b1
1mo ago Changed · +2 lines 13944cacb1f5
1mo ago Changed e52e742ab32f
1mo ago Changed · -6 lines cba3cf7afdb5
1mo ago Changed · +6 lines fe743e92c84a
2mo ago Changed be6058b120fc
2mo ago First seen · 315 lines · 52 tokens per session scan A 1c45f3b51bb7

Subscribe to this mod's changes

verify is a skill published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 52 tokens to every session and 4,540 once invoked, about $0.0002 per session on Opus 5.5. 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.

Research

verify next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verifyrobinslange/learning-loop	Skill	13	4d ago	Apache-2.0	A	52	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code