verify

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

In plain words
What is it for?
Use it to review one note, a group of notes, or notes on a topic, then produce a report and repair plan.
Why use it?
It helps catch weak structure, duplicate notes, broken references, and claims that sources do not support.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/robinslange/learning-loop/verify
Any agent
npx skills add robinslange/learning-loop --skill verify
Clone the repo
git clone --depth 1 https://github.com/robinslange/learning-loop

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,309 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00052 $0.04309
Opus 5 $0.00026 $0.02155
Sonnet 5 $0.00010 $0.00862
Haiku 4.5 $0.00005 $0.00431

Measured 2d ago against content hash 1c45f3b51bb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 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):

node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" '{"agent":"verify","skill":"verify","action":"session-start","intent":"SCOPE","config":{"note_count":N}}'

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

For each note with issues, run the stdin form (- + quoted heredoc) — finding_detail carries free text, and prose quotes/backticks/$ must not break shell quoting (escape only JSON's own " and \):

node "${CLAUDE_PLUGIN_ROOT}/scripts/provenance-emit.js" - <<'JSON'
{"agent":"verify","skill":"verify","action":"score","target":"note-filename.md","result":"fail","finding_type":"overclaim","finding_detail":"single RCT stated as consensus","trigger":"verify-manual","confidence":"clear","ambiguous_alt":""}
JSON

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 · 315 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. 2d 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 (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 52 tokens to every session and 4,309 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens