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 floomhq/moto --skill session-learngit clone --depth 1 https://github.com/floomhq/motoWrote 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/floomhq/moto/session-learn)<a href="https://agentmods.dev/skills/floomhq/moto/session-learn"><img src="https://agentmods.dev/badge/skills/floomhq/moto/session-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/floomhq/moto/session-learn"><img src="https://agentmods.dev/badge/skills/floomhq/moto/session-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 | $0.00089 | $0.01105 |
| Opus 5.5 | $0.00036 | $0.00442 |
| Sonnet 5.5 | $0.00018 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade B, and why
session-learn scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/ How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Learn
Analyzes past session transcripts and extracts actionable improvements: recurring workflows that should become skills, corrections that should become CLAUDE.md rules, persistent facts for MEMORY.md, and gaps in existing skills.
Phase 1: Gather Data
Run these in parallel:
# List recent sessions
session-recall --list 20
# Cross-session error/correction/retry analysis
session-recall --all 10 --report
# Correction and constraint patterns
session-recall --all 10 "correction|wrong|mistake|don't|never|always|stop"
# Repeated workflow patterns
session-recall --all 10 "deploy|send|check|create|build|update|push"
Also invoke MCP tools if available (they give richer structured output):
recall_report- error/retry/correction analysis with statsrecall_decisions- key decisions across sessionsrecall_searchwith keywords for targeted pattern search
Phase 2: Classify Each Finding
For each finding, assign exactly one category:
| Category | Threshold | Target |
|---|---|---|
| Skill candidate | 3+ occurrences across sessions | New ~/.claude/skills/<name>/SKILL.md |
| CLAUDE.md rule | 2+ occurrences, global constraint or correction | Append to ~/.claude/CLAUDE.md |
| MEMORY.md entry | Any count, persistent fact or preference | Append to ~/.claude/projects/-root/memory/MEMORY.md or topic file |
| Existing skill update | Any count, gap in current coverage | Edit existing ~/.claude/skills/<name>/SKILL.md |
Cross-reference against existing skills before proposing new ones:
ls ~/.claude/skills/
Read the description field of potentially overlapping skills to check for duplication before proposing a new skill.
Phase 3: Present Findings
Format the report as a table per category. Do NOT apply anything yet.
## Session Learning Report
### New Skill Candidates
| Workflow | Sessions seen | Current coverage gap | Proposed skill name |
|----------|--------------|----------------------|---------------------|
| ... | ... | ... | ... |
### New CLAUDE.md Rules
| Pattern observed | Evidence (sessions/count) | Proposed rule text |
|-----------------|--------------------------|-------------------|
| ... | ... | ... |
### MEMORY.md Updates
| Topic | Current state | Proposed addition |
|-------|--------------|-------------------|
| ... | ... | ... |
### Existing Skill Improvements
| Skill | Gap found | Proposed change |
|-------|-----------|----------------|
| ... | ... | ... |
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 · 136 lines · 89 tokens per session scan B 111fb4de034b
session-learn is a skill published in the GitHub repository floomhq/moto (32 stars, last pushed 4mo ago), licensed MIT. It adds 89 tokens to every session and 1,105 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
catchup
Restore context after /clear by summarizing recent work and project state.
learning
Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledge.
session
Session lifecycle management. Parent skill for session-related skills: learning (pattern extraction) and compact (context compression).
context-exclusion
Maintain .agent-no-read.md markers for approved generated directories using deterministic scripts. Use when configuring generated-code context exclusion or restoring markers after regeneration, not for ordinary ignore rules or OS permissions.
report
Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…