Git AI is a Git extension that records which agent, model, and prompts produced AI-generated code in a repository. It is for developers and teams that need line-level attribution and the surrounding context for code created with AI coding tools. The catalogue skills and instructions support using Git AI in agent-assisted development workflows.
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 git-ai-project/git-ai --skill prompt-analysisgit clone --depth 1 https://github.com/git-ai-project/git-aiWrote 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/git-ai-project/git-ai/prompt-analysis)<a href="https://agentmods.dev/skills/git-ai-project/git-ai/prompt-analysis"><img src="https://agentmods.dev/badge/skills/git-ai-project/git-ai/prompt-analysis/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/git-ai-project/git-ai/prompt-analysis"><img src="https://agentmods.dev/badge/skills/git-ai-project/git-ai/prompt-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 575 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 414 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- low Excessive Agency · line 568 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00010 | $0.04834 |
| Opus 5.5 | $0.00004 | $0.01934 |
| Sonnet 5.5 | $0.00002 | $0.00967 |
| Haiku 4.5 | $0.00001 | $0.00483 |
Grade B, and why
prompt-analysis 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**User:** `~/.claude/settings.json` Copies of this mod
1 near-identical copy found in the catalogue:
- prompt-analysis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Analysis Skill
Analyze AI prompting patterns using the local prompts.db SQLite database.
What is Git AI?
Git AI is a tool that tracks AI-generated code and prompts in git. It stores:
- Every AI conversation (prompts and responses)
- Which lines of code came from AI vs human edits
- Acceptance rates (how much AI code was kept vs modified)
- Associated commits and authors
This skill queries that data to help users understand their AI coding patterns.
Initialization
First, determine scope from the user's question:
| User mentions | Flags to use |
|---|---|
| "my prompts" or nothing specified | (default - current user, current repo) |
| "team", "everyone", "all authors" | --all-authors |
| specific person's name | --author "<name>" |
| specific time range | --since <days> (default: 30) |
Discovery is notes-only — git-ai prompts always operates on the current repository (the working directory must be inside a git repo). To analyze multiple repos, run the command separately in each.
Run initialization:
git-ai prompts [flags]
This creates/updates prompts.db in the current directory.
Schema Reference
The prompts table contains:
seq_id- Auto-increment ID for iterationid- Unique prompt identifiertool- Tool used (e.g., "claude-code", "cursor")model- Model name (e.g., "claude-sonnet-4-20250514")human_author- Git user who created the promptcommit_sha- Associated commit (if any)total_additions,total_deletions- Lines of code changedaccepted_lines,overridden_lines- Lines kept vs modified by humanaccepted_rate- Ratio: accepted / (accepted + overridden)messages- JSON array of the conversationstart_time,last_time- Unix timestamps
Analysis Approaches
For aggregate questions (metrics, comparisons)
Use direct SQL queries:
git-ai prompts exec "SELECT model, AVG(accepted_rate), COUNT(*) FROM prompts GROUP BY model"
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 · 588 lines · 10 tokens per session scan B 7437b81c30f7
prompt-analysis is a skill published in the GitHub repository git-ai-project/git-ai (2,899 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 4,834 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
kermt-pretrain-scratch
Pretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrainddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model…
cdf-auto-labeling
Use when a user needs to get started with CDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, configure a stage, or pull the prebuilt stage containers from NGC (nvcr.io). Confirm critical inputs (data path, output path, endpoints) and ask when any are…
prompt-lab
LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites. Triggers on: "prompt engineering", "generate prompt variants", "A/B test prompts", "optimize prompt", "improve this prompt". NOT for SKILL.md files, use skill-evaluator.
promptfoo-evals
Design and run promptfoo evaluations for LLM behavior regressions or comparisons across prompts, agent rules, and models. Use for repeatable behavioral cases with explicit assertions, not ordinary unit tests or static configuration checks.
prompt-engineering
Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows.…
ai-video-prompt-pack
Create, adapt, and review AI video generation prompt packs for tools such as Gemini/Veo, Sora, Runway, Pika, Luma, and similar systems. Use when Codex is asked for video generation prompts, Shorts prompts, AI ad concepts, timing maps, scene prompts, negative prompts, voiceover/audio directions, reference-image…