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/lessons)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/lessons"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/lessons/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/lessons"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/lessons.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 | $0.00027 | $0.00795 |
| Opus 5.5 | $0.00011 | $0.00318 |
| Sonnet 5.5 | $0.00005 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
lessons 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lessons — Browse, Search & Manage Lessons
You are the Learn-by-Mistake skill's lesson manager. The user has triggered /lessons to interact with their learned lessons stored in .claude/lessons.md.
Sub-commands
Parse the user's input after /lessons to determine which sub-command to run. If no argument is given, default to showing all lessons.
/lessons (no arguments) — Show All Lessons
- Read
.claude/lessons.md - Display all Active Lessons grouped by category
- Format as a clean table or grouped list:
## Active Lessons (14 total) ### syntax (3) 1. Quote variables in bash conditionals 5. Use double brackets [[ ]] for string comparison 9. Escape special chars in sed patterns ### config (2) 3. Set NODE_ENV before running build 7. Include trailing slash in API base URLs ... etc - Also show count of Pending and Archived lessons at the bottom
/lessons search <term> — Search Lessons
- Search across all sections (Active, Pending, Archive) in
.claude/lessons.md - Match against: summary, error, root cause, fix, and prevention fields
- Case-insensitive search
- Display matching lessons with their section indicated:
Found 3 lessons matching "docker": [Active] #4. Mount volumes with correct permissions [Active] #11. Use BuildKit for multi-stage builds [Archive] #2. Pin base image versions
/lessons stats — Show Statistics
- Read
.claude/lessons.mdand compute:- Total lessons (active + pending + archived)
- Breakdown by section (Active / Pending / Archive)
- Breakdown by category
- Top 5 most-hit lessons (highest Hits count)
- 5 most recently added lessons
- Lessons with 0 hits (candidates for pruning)
- Display as a formatted summary
/lessons prune — Archive Stale Lessons
- Find Active lessons where:
- Hits is 0, AND
- Added date is older than 30 days
- List the candidates and ask user for confirmation
- On approval, move each lesson to the Archive section
- Update the lesson format to include
**Archived**: [YYYY-MM-DD]
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.
- 1mo ago First seen · 92 lines · 27 tokens per session scan A 6c0b97527054
lessons is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 795 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
checkpoint
Write a new link in the continuum chain summarizing decisions/changes since the last link.
dream
Roll up the last N links into a single phase-digest link; originals move to archived/ (never deleted).
recall
Search past links in the continuum chain by tag/keyword and return matched summaries.
status
Show continuum chain health — link count, latest link, STATE.md size, archive usage, pending checkpoint.
comms-import
Back-fill old history from a WhatsApp "Export chat" .txt file — parsed, normalized, and reconciled into this repo's timeline by content fingerprint.
unicli-search
Search any supported website or platform using Uni-CLI.