git-ai-search

git-ai-search is a skill for Claude Code, Codex from git-ai-project/git-ai. It costs 13 tokens per session (2,513 once invoked), scanned A, original, Apache-2.0.

A search and restore tool for AI coding conversations saved by Git AI in Git history, the record of changes in a software project. It can connect earlier prompts and code changes to commits or files.

In plain words
What is it for?
Use it to find conversations by commit, file, line range, author, or keyword, view transcripts, and continue an earlier AI session.
Why use it?
It avoids losing the reasoning behind past AI-generated code when someone needs to understand or continue earlier work.

Skill for Claude CodeCodex

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/git-ai-project/git-ai/git-ai-search
Any agent
npx skills add git-ai-project/git-ai --skill git-ai-search
Clone the repo
git clone --depth 1 https://github.com/git-ai-project/git-ai

Made for: Claude Code, Codex.

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 git-ai-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/git-ai-project/git-ai/git-ai-search.svg)](https://agentmods.dev/skills/git-ai-project/git-ai/git-ai-search)
Your own site
<a href="https://agentmods.dev/skills/git-ai-project/git-ai/git-ai-search"><img src="https://agentmods.dev/badge/skills/git-ai-project/git-ai/git-ai-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,513 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 $0.00013 $0.02513
Opus 5 $0.00006 $0.01256
Sonnet 5 $0.00003 $0.00503
Haiku 4.5 $0.00001 $0.00251

Measured 4d ago against content hash 1838416874f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-ai-search 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.

skills/git-ai-search/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git AI Search Skill

Search and restore AI conversation context from git history using git-ai search and git-ai continue.

Overview

Git AI tracks AI-generated code and the conversations that produced it. This skill helps you:

  • Search - Find AI prompt sessions by commit, file, pattern, or author
  • Continue - Restore AI session context to continue work where someone left off
  • Show - View the full transcript of a specific prompt

When to Use Each Command

You want to... Use...
See what AI context exists for a commit git-ai search --commit <sha>
See AI context for specific lines git-ai search --file <path> --lines <range>
Read the full AI conversation git-ai search --commit <sha> --verbose
Get machine-readable output git-ai search --json
Find prompts mentioning a topic git-ai search --pattern "keyword"
Continue someone's AI session git-ai continue --commit <sha>
Continue working on a code region git-ai continue --file <path> --lines <range>
Launch Claude with restored context git-ai continue --commit <sha> --launch
View a specific prompt transcript git-ai show-prompt <id>

Workflow Patterns

1. Investigate a Commit

Understand what AI assistance was used in a specific commit:

# See a summary of AI sessions in the commit
git-ai search --commit abc1234

# View the full conversations
git-ai search --commit abc1234 --verbose

# Get JSON for programmatic processing
git-ai search --commit abc1234 --json | jq '.prompts | keys[]'

2. Understand a Code Region

Find what AI sessions contributed to specific lines:

# Search by file
git-ai search --file src/main.rs

# Search specific lines
git-ai search --file src/main.rs --lines 100-150

# Multiple line ranges
git-ai search --file src/main.rs --lines 50-75 --lines 200-250

3. Continue Someone's Work

Pick up where a teammate left off:

# See what they were working on
git-ai search --commit abc1234 --verbose

# Restore context and continue in your shell
git-ai continue --commit abc1234

# Or launch directly into Claude Code
git-ai continue --commit abc1234 --launch

# Or copy context to clipboard to paste elsewhere
git-ai continue --commit abc1234 --clipboard

Read the full file on GitHub · 390 lines

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 · 390 lines · 13 tokens per session scan A 1838416874f4

Subscribe to this mod's changes

git-ai-search is a skill published in the GitHub repository git-ai-project/git-ai (2,533 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 2,513 once invoked, about $0.0001 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

html-ppt-zhangzara-coral

OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.

nexu-io/open-design · 55 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

deepstream-sop

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…

NVIDIA/skills · 219 tokens

cupynumeric-migration-readiness

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…

NVIDIA/skills · 173 tokens