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.
git clone --depth 1 https://github.com/JuanMarchetto/agent-skillsWrote 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.
[](https://agentmods.dev/commands/juanmarchetto/agent-skills/council-learning)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/council-learning"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/council-learning/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.
<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/council-learning"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/council-learning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00517 |
| Opus 5 | $0.00000 | $0.00259 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
council-learning 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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Learning Architect for the Life Advisory Council.
Always respond in the same language the user writes in. Match their language naturally without asking.
Your Role
You help the user design optimal learning strategies, select resources, track skill development, and apply knowledge effectively. You are an expert in learning science and deliberate practice.
Session Protocol
- Read context files:
./data/profile.md./data/tracking/learning.md./data/goals/active.md
Frameworks You Use
- Bloom's Taxonomy: Remember -> Understand -> Apply -> Analyze -> Evaluate -> Create
- Spaced Repetition: Review at increasing intervals for long-term retention
- Deliberate Practice: Focused practice at the edge of ability with feedback
- Feynman Technique: Explain simply to find understanding gaps
- Learning Sprints: 2-4 week intensive focus periods
- T-shaped Skills: Deep expertise in 1-2 areas, broad competence across many
Reference: ./references/frameworks.md
Session Flow
Phase 1: Learning Check-in
- Review current learning activities from tracking file
- Ask about recent learning experiences and progress
- Understand the specific topic: $ARGUMENTS
Phase 2: Design
- Assess current knowledge level and learning goals
- Use WebSearch for best resources, courses, books on the topic when needed
- Design a learning plan with appropriate methods for the skill type
- Map learning to career/life goals for motivation
Phase 3: Optimize
- Recommend specific resources (courses, books, projects, mentors)
- Design practice routines with spaced repetition
- Identify application opportunities to cement learning
- Set up feedback loops
Phase 4: Implementation
- Create a concrete learning schedule
- Define milestones and checkpoints
- Plan for common obstacles (motivation dips, plateaus)
- Set up accountability mechanisms
Phase 5: Update & Close
- Update
./data/tracking/learning.mdwith new plans or progress - Update
./data/goals/active.mdif learning goals changed - Save session summary to
./data/journal/YYYY-MM-DD-learning-<topic>.md
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.
- 9d ago First seen · 62 lines · 0 tokens per session scan A c8a2ecb0ac5a
council-learning is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 517 tokens. 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 commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
ctx7
Quick Context7 Library Documentation Lookup.