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 skills add rijuvashisht/Magneto --skill learngit clone --depth 1 https://github.com/rijuvashisht/MagnetoWrote 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/skills/rijuvashisht/magneto/learn)<a href="https://agentmods.dev/skills/rijuvashisht/magneto/learn"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/learn/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/skills/rijuvashisht/magneto/learn"><img src="https://agentmods.dev/badge/skills/rijuvashisht/magneto/learn.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 | $0.00434 |
| Opus 5 | $0.00000 | $0.00217 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00043 |
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 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.
What it actually says
/learn — Manage Persistent Magneto Memory
Role: Memory Manager
Inputs: optional query, tags, or new learning
Outputs: .magneto/memory/ updates
Audit actions: learn.recorded, learn.pruned, learn.exported
What /learn Does
Magneto's memory store is a cross-session knowledge base of:
- Patterns — coding conventions established in the codebase
- Anti-patterns — things that were explicitly rejected
- Decisions — architectural choices with rationale
- Bugs — past bug + fix pairs for regression memory
- Personas — user-specific preferences
This skill manages that store.
Subcommands
View
magneto learn list # recent learnings
magneto learn search <query> # semantic/keyword search
magneto learn show --tag patterns
Record
magneto learn save --tags pattern "When error Result<T>, the error branch must include a requestId"
magneto learn save --tags anti-pattern "Don't inline configuration; load via src/config/*"
Manage
magneto learn prune --older-than 90d --importance-below 3
magneto learn export > learnings.json
magneto learn import learnings.json
When to Record
- After /retro identifies a pattern or anti-pattern
- After /review catches a repeated mistake
- After /investigate resolves a novel bug
- After user explicitly says "remember this"
When NOT to Record
- One-off decisions that don't generalize
- Things the graph already captures (module structure)
- Private data (never record credentials or PII)
Trigger Phrases
- "remember this"
- "save this learning"
- "what do you know about"
- "show me memory"
Contract Reminder
- Never save credentials or PII
- Always tag new learnings for later retrieval
- Prefer updating existing memory over creating duplicates
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 · 68 lines · 0 tokens per session scan A 1104aec6f684
learn is a skill published in the GitHub repository rijuvashisht/Magneto (6 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 434 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 skills, from other repositories
knowledge-wiki
Manage the personal knowledge wiki. Use when the user shares articles, documents, or asks to organize knowledge; when a conversation produces insights worth preserving as structured knowledge; or when the user asks about the knowledge base.
session-logs
Search and analyze your own session logs (older/parent conversations) using jq.
ax-agent-memory-skills
This skill helps an LLM generate correct AxAgent memory retrieval, context-map, and dynamic skill-loading code using @ax-llm/ax. Use when the user asks about contextMap, AxAgentContextMap, onMemoriesSearch, memoriesCatalog, recall(...), inputs.memories, onLoadedMemories, onUsedMemories, onSkillsSearch, skillsCatalog…
ax-cpp-agent-memory-skills
Use when writing C++ code with axllm for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
ax-go-agent-memory-skills
Use when writing Go code with github.com/ax-llm/ax/packages/go for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
ax-python-agent-memory-skills
Use when writing Python code with axllm for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.