agentmods.dev

gaps

gaps is a skill for Claude Code from robinslange/learning-loop. It costs 94 tokens per session (2,956 once invoked), scanned A, original, Apache-2.0.

A note-review tool that examines a knowledge vault for missing evidence, weak claims, unanswered questions, and opposing views.

In plain words
What is it for?
Use it to review one topic, automatically choose an unexamined topic, or scan the main topic groups in a vault at a chosen depth.
Why use it?
It helps reveal where your notes are incomplete or too confident, instead of letting gaps remain hidden as the vault grows.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the learning-loop plugin — 24 skills, 20 agents, 7 hooks shipped together

not rated 13repo changed 1mo ago A scan 94 tokens original Apache-2.0

Good fit Use it to review one topic, automatically choose an unexamined topic, or scan the main topic groups in a vault at a chosen depth.

Compare 6 skills from other repositories ↓
View source ↗ 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.

agentmods badge for gaps

README.md
[![agentmods](https://agentmods.dev/badge/skills/robinslange/learning-loop/gaps/github.svg)](https://agentmods.dev/skills/robinslange/learning-loop/gaps)
Your own site
<a href="https://agentmods.dev/skills/robinslange/learning-loop/gaps"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/gaps/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 gaps

Your own site · 80×15
<a href="https://agentmods.dev/skills/robinslange/learning-loop/gaps"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/gaps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,956 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 $0.00094 $0.02956
Opus 5.5 $0.00038 $0.01182
Sonnet 5.5 $0.00019 $0.00591
Haiku 4.5 $0.00009 $0.00296

Measured 1mo ago against content hash 63a46f7a68a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gaps 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/gaps/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gaps: Epistemic Gap Analysis

Overview

The vault grows by accumulation. /gaps shakes the cage. It surfaces tensions, questions absences, and flags thin ice. The truth doesn't need to defend itself: weak beliefs get questioned, strong beliefs get stress-tested.

When to Use

  • /gaps "topic": focused analysis on a specific topic
  • /gaps: auto-picks the densest unchallenged cluster in the vault
  • /gaps --sweep: runs across all major domain clusters

Parameters

Parse from the invocation. All have defaults.

Parameter Options Default
topic any string auto-pick if absent
depth shallow / medium / deep scales to note maturity
sweep flag off
dry-run flag off

Depth auto-scaling:

  • Permanent notes → deep
  • Fleeting notes → medium
  • Inbox notes → shallow
  • Mixed maturity → use the highest

Provenance

This skill emits provenance events for pipeline observability. Run each Bash command silently.

At session start (after scope identified):

ll-run provenance-emit.js '{"agent":"gaps","skill":"gaps","action":"session-start","intent_kind":"topic","config":{"depth":"DEPTH"}}'

At session end. Alongside the existing counters, include the common outcome shape: items_in (notes analysed), items_out (notes analysed minus tensions plus counterpoints created), items_flagged (thin_ice), duration_ms:

ll-run provenance-emit.js '{"agent":"gaps","skill":"gaps","action":"session-end","notes_analysed":N,"counterpoints_created":N,"rewrites":N,"thin_ice":N,"tensions":N,"blindspots":N,"items_in":N,"items_out":N,"items_flagged":N,"duration_ms":N}'

Per-note tracking is handled automatically by the PostToolUse hook.

Process

Step -1: Parameter Resolution

No arguments (/gaps): Run auto-pick immediately (find the densest unchallenged cluster — see Step 0). After presenting results, mention the alternatives in one line:

Analysed [cluster]. Alternatives: /gaps "topic" for a specific domain, /gaps --sweep across all clusters, --depth shallow|medium|deep to override maturity scaling.

Read the full file on GitHub · 258 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. 1mo ago Changed 63a46f7a68a3
  2. 1mo ago Changed 772f6d3e6285
  3. 1mo ago Changed · -2 lines 073de7448e0a
  4. 1mo ago Changed · +2 lines be1baccf09bd
  5. 2mo ago Changed 8f54f84df7a7
  6. 2mo ago First seen · 258 lines · 94 tokens per session scan A 3fa12e37db54

Subscribe to this mod's changes

gaps is a skill published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,956 once invoked, about $0.0004 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.

Learning and teachingResearch
Related

gaps compared with skills from other repositories

gaps next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gapsrobinslange/learning-loopSkill134d agoApache-2.0A94Claude Code
hr-onboardingnexu-io/open-designSkill106kyesterdayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32kyesterdayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA81Claude Code
eli5companion-inc/feynmanSkill10k6d agoMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4k25d agoApache-2.0A25Claude Code, Codex