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 commands/sakrut/ai-code-graph/learngit clone --depth 1 https://github.com/sakrut/ai-code-graphWhat 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 | $0.00000 | $0.00691 |
| Opus 5 | $0.00000 | $0.00345 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
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.
This is a copy
94% identical to learn — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn
Arguments: $ARGUMENTS Learn about Task Master capabilities through interactive exploration.
Arguments: $ARGUMENTS
Interactive Task Master Learning
Based on your input, I'll help you discover capabilities:
1. What are you trying to do?
If $ARGUMENTS contains:
- "start" / "begin" → Show project initialization workflows
- "manage" / "organize" → Show task management commands
- "automate" / "auto" → Show automation workflows
- "analyze" / "report" → Show analysis tools
- "fix" / "problem" → Show troubleshooting commands
- "fast" / "quick" → Show efficiency shortcuts
2. Intelligent Suggestions
Based on your project state:
No tasks yet?
You'll want to start with:
1. /project:task-master:init <prd-file>
→ Creates tasks from requirements
2. /project:task-master:parse-prd <file>
→ Alternative task generation
Try: /project:task-master:init demo-prd.md
Have tasks? Let me analyze what you might need...
- Many pending tasks? → Learn sprint planning
- Complex tasks? → Learn task expansion
- Daily work? → Learn workflow automation
3. Command Discovery
By Category:
- 📋 Task Management: list, show, add, update, complete
- 🔄 Workflows: auto-implement, sprint-plan, daily-standup
- 🛠️ Utilities: check-health, complexity-report, sync-memory
- 🔍 Analysis: validate-deps, show dependencies
By Scenario:
- "I want to see what to work on" →
/project:task-master:next - "I need to break this down" →
/project:task-master:expand <id> - "Show me everything" →
/project:task-master:status - "Just do it for me" →
/project:workflows:auto-implement
4. Power User Patterns
Command Chaining:
/project:task-master:next
/project:task-master:start <id>
/project:workflows:auto-implement
Smart Filters:
/project:task-master:list pending high
/project:task-master:list blocked
/project:task-master:list 1-5 tree
Automation:
/project:workflows:pipeline init → expand-all → sprint-plan
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 · 106 lines · 0 tokens per session scan A 494976da16fb
learn is a command published in the GitHub repository sakrut/ai-code-graph (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 691 tokens. A static security scan graded it A with 0 findings. It is 94% identical to learn, differing in 7 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.