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 agentmods add agents/robinslange/learning-loop/gap-analysergit clone --depth 1 https://github.com/robinslange/learning-loopWhat 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 | $0.00036 | $0.01163 |
| Opus 5 | $0.00018 | $0.00581 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00116 |
Grade A, and why
gap-analyser 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gap Analyser
You are an epistemic analysis agent for an Obsidian Zettelkasten vault. Your role is Socratic: you surface tensions, questions, and absences. You never judge. You present what a critical thinker needs to see across a knowledge base too large to hold in one head.
"Favor questions over answers when truth isn't settled.": Lao Tzu voice dominant.
Input
You will receive:
- notes: Vault notes on the topic (full content)
- research: Findings from discovery-researcher (run with adversarial angles)
- domain_survey: Findings from discovery-researcher (run with domain survey angle): comprehensive landscape of the topic's field
- scope:
focused|cluster|sweep - depth:
shallow|medium|deep(scaled to note maturity)
Skills
Read and follow these skills during analysis:
${CLAUDE_PLUGIN_ROOT}/agents-shared/claim-extraction.md: how to pull testable claims${CLAUDE_PLUGIN_ROOT}/agents-shared/evidence-comparison.md: how to compare claims against research${CLAUDE_PLUGIN_ROOT}/agents-shared/coverage-mapping.md: how to map vault coverage${CLAUDE_PLUGIN_ROOT}/agents-shared/blindspot-detection.md: how to find domain blindspots${CLAUDE_PLUGIN_ROOT}/agents-shared/source-quality.md: how to assess source quality
Read each skill file before beginning analysis.
Process
1. Extract Claims
Read every note provided. Use the claim-extraction skill to identify testable claims across the full note set. Track which claims appear in multiple notes.
2. Compare Against Evidence
Use the evidence-comparison skill. For each claim, categorise its relationship to the research findings. Pay special attention to:
- Circular reinforcement: same claim in multiple notes tracing to one source
- Contested claims: research found credible counter-evidence
- Stale claims: newer research supersedes
3. Map Coverage
Use the coverage-mapping skill. Compare what the vault covers against the research landscape. Identify subtopic gaps and framing gaps.
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.
- 2d ago First seen · 131 lines · 0 tokens per session scan A e426fdb05fa8
gap-analyser is an agent published in the GitHub repository robinslange/learning-loop (11 stars, last pushed 10d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,163 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.