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/hainrixz/aprende-skill/aprendegit clone --depth 1 https://github.com/Hainrixz/aprende-skillWrote 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/hainrixz/aprende-skill/aprende)<a href="https://agentmods.dev/commands/hainrixz/aprende-skill/aprende"><img src="https://agentmods.dev/badge/commands/hainrixz/aprende-skill/aprende.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00633 |
| Opus 5 | $0.00020 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
aprende 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 4d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aprende — Learn from this conversation
You are being invoked as the /aprende slash command. Follow the exact workflow documented in the aprende skill:
Skill location:
- Plugin install:
${CLAUDE_PLUGIN_ROOT}/skills/aprende/SKILL.md - Manual install:
~/.claude/skills/aprende/SKILL.md
Read that file end-to-end before doing anything. Then execute the 5-pass workflow:
- Pass A — Scan the conversation for correction signals (see
references/signal-patterns.md). - Pass B — Generate a candidate list with confidence labels (
high|medium|low). Cap at 15. - Pass C — Dedup against existing
MEMORY.md, installed skills, andCLAUDE.md/AGENTS.md. Annotate overlaps, never drop silently. - Pass D — Confirm by printing the exact template in
prompts/confirmation-template.md. WAIT for user reply. Do not call any file-mutating tool yet. - Pass E — Execute the per-category writes (see
references/memory-format.mdandreferences/lesson-format.mdfor exact frontmatter). One confirmation line per write.
Arguments / Argumentos
The slash command accepts these argument forms via $ARGUMENTS:
$ARGUMENTSempty → standard run.$ARGUMENTS = --review→ run/aprende --reviewmode: revisit existing lessons, mark retired or refresh. Seereferences/review-workflow.md.$ARGUMENTS = --portable→ standard run + mirror lessons to./.aprende/for Codex compatibility. See SKILL.md section 7.$ARGUMENTS = --dry-run→ execute Pass A, B, C, D, but skip Pass E entirely. Print "(dry-run: no files written)" at the end. Useful for previewing what would be captured without committing.
If $ARGUMENTS contains an unrecognized flag, print the allowed flags and exit.
The one rule that matters
Never write to disk before the user confirms in Pass D. No Write, no Edit, no destructive Bash. Read-only is the only permitted state between Pass D's output and the user's reply.
Nunca escribas a disco antes de la confirmación del Pase D.
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.
- 4d ago First seen · 50 lines · 40 tokens per session scan A 0de1296206eb
aprende is a command published in the GitHub repository Hainrixz/aprende-skill (23 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 633 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 commands, from other repositories
retro
Post-work command that extracts learnings and updates the learning registry.
ingest-review
Ingest PR review feedback into agent memory for continuous learning. Provide PR number.
learning
Learning hub - evaluate sessions, view patterns, teach preferences.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
session-end
I'll summarize this coding session and update the memory system with our accomplishments.