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/florianbruniaux/claude-code-plugins/git-ai-archaeologynpx skills add FlorianBruniaux/claude-code-plugins --skill git-ai-archaeologygit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote 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/florianbruniaux/claude-code-plugins/git-ai-archaeology)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-plugins/git-ai-archaeology"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-plugins/git-ai-archaeology.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.02641 |
| Opus 5 | $0.00023 | $0.01321 |
| Sonnet 5 | $0.00009 | $0.00528 |
| Haiku 4.5 | $0.00005 | $0.00264 |
Grade A, and why
git-ai-archaeology 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-ai-archaeology
Produces a complete analysis of AI config evolution in a git repository. Finds when each AI configuration file was created, how AI-config commit velocity evolved month by month, which PRs structured the evolution, and identifies maturity phases.
Output: a single file {output_dir}/{slug}-git-archaeology.md
Expected Input
/git-ai-archaeology repo_path=/path/to/repo [output=./talks/slug] [slug=talk-name] [since=2025-01-01]
repo_path: absolute path to the target git repo (required)output: output directory (default:./talks)slug: output filename (default: repo folder name)since: analysis start date (default: first repo commit)
Workflow
- Verify the repo: ensure the path exists and is a git repo
- Global metrics: total commits, releases, contributors, time period
- Section 1: First commits: find creation date for key AI-config paths
- Section 2: Monthly distribution: commits filtered by AI-config keywords
- Section 3: Major PRs: extract and categorize significant AI-config commits
- Section 4: CHANGELOG: if CHANGELOG.md exists, extract releases with AI mentions
- Section 5: Phases: synthesize evolution phases
- Save the output file
Step 1: Verification and Global Metrics
# Verify it's a git repo
git -C {repo_path} rev-parse --git-dir
# Global metrics
git -C {repo_path} log --oneline | wc -l # total commits
git -C {repo_path} tag --sort=version:refname | wc -l # total releases
git -C {repo_path} shortlog -sn --no-merges | wc -l # contributors
git -C {repo_path} log --pretty=format:"%ad" --date=short | tail -1 # first commit
git -C {repo_path} log --pretty=format:"%ad" --date=short | head -1 # last commit
git -C {repo_path} log --merges --oneline | wc -l # merged PRs
Step 2: Section 1: First Commits per AI-Config Path
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.
- 6d ago First seen · 334 lines · 47 tokens per session scan A f3f59f5522ed
git-ai-archaeology is a skill published in the GitHub repository FlorianBruniaux/claude-code-plugins (40 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 2,641 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.
Other skills, from other repositories
analytics
Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed project IDs. Supports time-range filtering and comparative analysis. Use when reviewing performance, estimating costs…
doctor
OrchestKit doctor for health diagnostics across manifest integrity, hook configuration, skill validation, agent frontmatter, MCP server connectivity, CC version compatibility, and permission rules. Reports issues with severity levels and auto-remediation suggestions. Validates component counts, detects orphaned…
setup
创建一个新的 Workframe 项目,或把已有项目接入 Workframe。按用户意图与目标目录状态分流(新建 / 接入),对话采集业务上下文后落骨架、订阅 core 插件、完成落盘验收。仅用于 Workframe 框架的项目初始化,不承担 npm init / create-react-app / git init 等通用脚手架。.
code-review
代码审查,从需求符合度/正确性/安全性/可维护性/性能五维度评审代码变更,输出风险分级的 Finding 列表.
html-demo
仿真型 HTML 交互 demo 生成:按用户截图复刻真实界面,产出自包含、全状态可达(带模拟开关)的可交互单文件 demo,落 tmp/ 就地多轮迭代;拍板后归档 prototypes/ 并衔接 prd-writer「demo 先行变体」写 PRD。.
technical-design
技术方案设计与实施,提供轻量路径(小改动直接落地)和完整路径(架构/数据/API/多文件高风险变更走完整方案+实施+交付)双档分流.