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 skills/zircote/git-notes-memory/memory-assistantnpx skills add zircote/git-notes-memory --skill memory-assistantgit clone --depth 1 https://github.com/zircote/git-notes-memoryWhat 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 | $0.00196 | $0.03867 |
| Opus 5 | $0.00098 | $0.01934 |
| Sonnet 5 | $0.00039 | $0.00773 |
| Haiku 4.5 | $0.00020 | $0.00387 |
Grade A, and why
memory-assistant 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.
How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Assistant Skill
A comprehensive skill that facilitates memory capture, recall, and lifecycle management for the git-notes-memory plugin. This skill helps Claude proactively suggest memory captures, surface relevant context, and reinforce persistent memory practices.
Purpose
This skill serves as an intelligent memory assistant that:
- Detects capture opportunities - Recognizes decisions, learnings, blockers, and patterns worth preserving
- Surfaces relevant context - Proactively recalls memories when working on related topics
- Guides best practices - Helps users get maximum value from the memory system
- Maintains memory hygiene - Suggests reviews, updates, and lifecycle management
Core Workflows
Workflow 1: Capture Detection
When the conversation reveals content worth preserving, this skill activates to guide capture.
Decision Detection
Trigger patterns: "decided to", "choosing", "we'll use", "going with", "selected"
# Detect decision-worthy content
decision_signals = [
"decided to", "choosing", "we'll use", "going with",
"selected", "will implement", "the approach is"
]
# If detected, suggest capture:
"""
💡 **Decision detected**: You just made an architectural choice.
Would you like to capture this decision for future reference?
Use: `/memory:capture decisions <summary> -- <rationale>`
Example: `/memory:capture decisions Use PostgreSQL for data layer -- JSONB support and team familiarity outweigh SQLite simplicity`
"""
Learning Detection
Trigger patterns: "TIL", "learned that", "discovered", "found out", "realized", "turns out"
learning_signals = [
"TIL", "learned that", "discovered", "found out",
"realized", "turns out", "didn't know", "interesting that"
]
# If detected, suggest capture:
"""
💡 **Learning detected**: You discovered something worth remembering.
Use: `[remember] <insight>` inline, or
`/memory:capture learnings <summary>`
"""
Blocker Detection
Trigger patterns: "stuck on", "blocked by", "cannot", "impediment", "failing"
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 479 lines · 196 tokens per session scan A f4628ff6f826
memory-assistant is a skill published in the GitHub repository zircote/git-notes-memory (4 stars, last pushed 8mo ago), licensed MIT. It adds 196 tokens to every session and 3,867 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
rudder-data-graphs
Produces Data Graph YAML from RETL sources for Audiences. Use when designing Data Graphs, mapping RETL to entities/events, or assessing customer fit for Audiences.
rudder-cli-workflow
Validates, previews, and applies RudderStack resource changes via YAML specs. Use when iterating on RudderStack resources with rudder-cli - validates specs, previews changes with dry-run, and applies changes to workspaces.
rudder-transformations
Creates and manages RudderStack transformations and libraries with local testing. Use when creating, editing, or managing RudderStack transformations and transformation libraries using the Rudder CLI.
rudder-typer-workflow
Generates type-safe SDKs (Swift/Kotlin) from tracking plans with compile-time validation. Use when generating type-safe event tracking code from tracking plans using RudderTyper.
rudder-code-first-instrumentation
Derives tracking plans from existing codebase types and structures. Use when instrumenting an existing product that wasn't well-instrumented or restructuring existing tracking.
rudder-data-catalog
Creates and manages events, properties, categories, and custom types for instrumentation schemas. Use when creating or managing events, properties, categories, or custom types for RudderStack instrumentation.