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.
git clone --depth 1 https://github.com/fatihkan/badiWrote 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/commands/fatihkan/badi/plugin)<a href="https://agentmods.dev/commands/fatihkan/badi/plugin"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/plugin.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 | $0.00000 | $0.00778 |
| Opus 5 | $0.00000 | $0.00389 |
| Sonnet 5 | $0.00000 | $0.00156 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
plugin 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 today.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin management command. Installs, removes, and lists plugins in the Badi system.
Required Tools
- Bash (git clone, npm install, file copy)
- Read (manifest files, current configuration)
- Write (configuration updates, file creation)
- ...
Subcommands
This command has three subcommands:
install <source>- Install a new pluginremove <name>- Remove a pluginlist- List installed plugins
If the user did not specify a subcommand, ask which one they want.
Subcommand: install
Step 1: Source Type Detection
- If a git URL (ends with
.gitor containsgithub.com): git source - If an npm package name: npm source
- If a local directory path: local source
- ...
Step 2: Download the Plugin
For a git source:
git clone [URL]into a temporary directory- Check the
badi-plugin.jsonmanifest file - If there is no manifest, ERROR and stop
For an npm source:
- Download the package with
npm pack [package] - Extract into a temporary directory
- Check the
badi-plugin.jsonmanifest file
For a local source:
- Verify
badi-plugin.jsonexists in the given directory
Step 3: Read and Validate the Manifest
Read and validate badi-plugin.json:
[abridged]
Required fields: name, version
ERROR and stop on an invalid manifest.
Step 4: Conflict Check
- Check whether a plugin with the same name is installed
- Verify added commands do not collide with existing commands
- Check agent name collisions
- ...
Step 5: Copy the Files
- Create the
.claude/plugins/[plugin-name]/directory - Copy the manifest file
- Copy agent files under
.claude/agents/ - ...
Step 6: Index Update
- Add the new commands to
command-index.mdwith a[Plugin]tag - Example format:
| /plugin-command | Description [Plugin: plugin-name] | - Add new hook references to settings.json (if needed)
Step 7: Install Verification
- Verify all files copied successfully
- Suggest running
/doctor - Show an install summary
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.
- today First seen · 116 lines · 0 tokens per session scan A 8179601bc907
plugin is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 778 tokens. 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 2026-09-06.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524) — sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
qa
Systematic QA testing of a web application — diff-aware, tiered, with fix-and-verify loop.
review-pr
Perform a comprehensive code review of a pull request.
security-audit
Comprehensive security audit with scored posture assessment.