memorix-git-memory

memorix-git-memory is a skill for Claude Code, Codex from AVIDS2/memorix. It costs 31 tokens per session (292 once invoked), scanned A, original, Apache-2.0.

A guide for using MemoraX Git Memory, which stores and searches evidence from a Git repository's commit history. Git is the system commonly used to track code changes over time.

In plain words
What is it for?
Use it to search change history, inspect stored commit details, ingest commits, backfill history, or install automatic post-commit recording.
Why use it?
It makes it easier to find what changed, when it changed, which files were touched, and which commit introduced a fix.

Skill for Claude CodeCodex

Part of the memorix plugin — 8 skills, 5 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/avids2/memorix/memorix-git-memory
Any agent
npx skills add AVIDS2/memorix --skill memorix-git-memory
Clone the repo
git clone --depth 1 https://github.com/AVIDS2/memorix

Made for: Claude Code, Codex.

Or install memorix, the plugin that ships this one along with the rest of its 8 skills, 5 hooks, 1 MCP server.

Wrote 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.

agentmods badge for memorix-git-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/avids2/memorix/memorix-git-memory.svg)](https://agentmods.dev/skills/avids2/memorix/memorix-git-memory)
Your own site
<a href="https://agentmods.dev/skills/avids2/memorix/memorix-git-memory"><img src="https://agentmods.dev/badge/skills/avids2/memorix/memorix-git-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00292
Opus 5 $0.00015 $0.00146
Sonnet 5 $0.00006 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 4d ago against content hash 562473ac682c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memorix-git-memory 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.

plugins/claude/memorix/skills/memorix-git-memory/SKILL.md · 27 lines

What it actually says

Memorix Git Memory

Use Git Memory for repository evidence. Use reasoning memory for intent.

Tool Router

Situation Prefer CLI fallback
Search what changed memorix_search with a change-focused query memorix memory search --query "what changed <topic>"
Inspect a git-backed memory memorix_detail memorix memory detail --id <id>
Ingest current commit manually CLI memorix ingest commit
Ingest a specific commit CLI memorix ingest commit --ref <ref>
Backfill recent history CLI memorix ingest log --count 20
Install post-commit ingestion CLI memorix git-hook --force

Retrieval Rules

  • Prefer Git Memory for "what changed", "when did this ship", "which files were touched", and "which commit introduced this".
  • Prefer reasoning memory for "why did we choose this", "what alternatives existed", and "what risk did we accept".
  • Cross-link important decisions with relatedCommits when storing reasoning.
  • Do not force-ingest noisy commits unless the skipped commit is genuinely important evidence.
Changes

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.

  1. 4d ago First seen · 27 lines · 31 tokens per session scan A 562473ac682c

Subscribe to this mod's changes

memorix-git-memory is a skill published in the GitHub repository AVIDS2/memorix (717 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 292 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.

Related

Other skills, from other repositories

init-workspace-documentation

Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.

griddynamics/rosetta · 10 tokens

graph

Initialize or refresh the knowledge-graph snapshot for a repository. Ensures the codebase-memory-mcp engine is present (fetching it if needed), then builds draft/graph/ and reports engine, counts, hotspots, and cycles. Accepts an optional repo path.

drafthq/draft · 56 tokens

deepnote

DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.

deepelementlab/jupyter-studio · 25 tokens

aide-handoff

Record current pipeline state to .aide/session.aide — the project-wide pipeline-position log that lets the next session (yours or another agent's) resume from a known point. CREATE on first invocation per feature; UPDATE on every subsequent meaningful transition. This skill is the orchestration layer: it detects…

aidemd-mcp/server · 226 tokens

brain

Signpost to the brain — an external, team-shareable knowledge store that holds context too durable for the repo and too cross-project for any single codebase (domain research, coding playbook, project history, journal, environment, identity, references). When the current task needs knowledge that isn't in the working…

aidemd-mcp/server · 145 tokens

strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

deepelementlab/jupyter-studio · 27 tokens