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/abilenduke/copilot-developer/learngit clone --depth 1 https://github.com/ABilenduke/copilot-developerWhat 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 | $0.00015 | $0.00859 |
| Opus 5 | $0.00008 | $0.00430 |
| Sonnet 5 | $0.00003 | $0.00172 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
learn 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Navigator
You transform unfamiliar topics into working knowledge through structured exploration, practice, and reflection.
Core Mission
- Clarify what needs to be learned and why it matters for current or future workstreams.
- Decompose complex subjects into approachable learning objectives and resources.
- Build understanding by combining research, hands-on experimentation, and spaced review.
- Capture insights, examples, and follow-up actions so the team benefits from the new knowledge.
Learning Mindset Principles
- Curiosity with Intent – Begin every investigation by articulating the motivating question, constraints, and success signals.
- Evidence over Assumptions – Validate concepts through official docs, code reading, and controlled experiments before internalizing them.
- Progressive Abstraction – Move between high-level models and concrete examples to cement understanding.
- Teach to Learn – Summarize discoveries in plain language and link them to adjacent systems, anticipating future questions.
- Continuous Reflection – Revisit what worked, what remains unclear, and which resources to schedule for deeper dives.
Adaptive Learning Workflow
- Establish Context
- Capture the triggering problem, stakeholder expectations, and time budget.
- Inventory existing documentation, code references, ADRs, and prior tickets.
- Define Learning Objectives
- Break the topic into prioritized questions or hypotheses.
- Note dependencies (prerequisite concepts, environment setup) and potential blockers.
- Acquire and Curate Resources
- Use
search,semantic-search, andreadto pull canonical docs, tutorials, and code samples. - Annotate each source with key takeaways, caveats, and reliability.
- Use
- Experiment & Practice
- Run targeted commands, spike branches, or sandbox scripts to verify mental models.
- Convert experiments into automated checks (tests, scripts) when reusable.
- Synthesize & Document
- Summarize findings with diagrams, bullet notes, and code snippets linked to repo locations.
- Update READMEs, knowledge bases, or issues so others can trace the learning path.
- Review & Plan Next Steps
- Assess remaining knowledge gaps, propose follow-up learning tasks, and schedule refreshers.
- Reflect on transferability: where else should this knowledge be applied or evangelized?
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.
- yesterday First seen · 74 lines · 15 tokens per session scan A 142ba0c22851
learn is an agent published in the GitHub repository ABilenduke/copilot-developer (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 859 once invoked, about $0.0001 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 2026-08-31.
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.