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 commands/anilcancakir/claude-code-plugins/my_projectgit clone --depth 1 https://github.com/anilcancakir/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/commands/anilcancakir/claude-code-plugins/my_project)<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugins/my_project"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugins/my_project.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 | $0.00048 | $0.01966 |
| Opus 5 | $0.00024 | $0.00983 |
| Sonnet 5 | $0.00010 | $0.00393 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade B, and why
my_project 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 3d 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.
grep -l "idea-research" ~/.claude/settings.json .claude/settings.json .claude/settings.local.json 2>/dev/null | head -1 How it starts
The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/my_project - Project Brief Generator
Create a comprehensive project.md brief through an interactive workflow. This is NOT technical documentation - it defines WHAT the project is and WHY it exists.
Arguments
- No arguments: Full interactive workflow
--quick: Minimal project brief (name, description, slogan)--research: Include market research via idea-research plugin
Output: project.md
A non-technical project brief containing:
- Project identity (name, tagline, description)
- Problem statement (what pain it solves)
- Target audience (who it's for)
- Value proposition (why it's unique)
- Core features (what it does, not how)
- Success metrics (how to measure success)
Workflow
Phase 1: Project Discovery
Check for existing project context:
# Check for existing project.md
ls -la project.md PROJECT.md 2>/dev/null
# Check package.json for name/description
cat package.json 2>/dev/null | head -20
# Check composer.json
cat composer.json 2>/dev/null | head -20
# Check pubspec.yaml
cat pubspec.yaml 2>/dev/null | head -20
Phase 2: Interactive Identity Creation
Ask user for project fundamentals:
PROJECT IDENTITY
================
Let's define your project's core identity.
1. PROJECT NAME
What is your project called?
[Detected: "my-app" from package.json]
2. TAGLINE (One sentence)
A memorable phrase that captures your project's essence.
Examples:
- "Build faster, ship sooner"
- "Your finances, simplified"
- "The last CRM you'll ever need"
3. DESCRIPTION (2-3 sentences)
What does your project do? Who is it for?
Focus on the BENEFIT, not the technology.
Good: "A task manager that helps busy professionals
stay organized without the complexity."
Avoid: "A React app with Redux and PostgreSQL
that manages tasks."
Phase 3: Problem & Solution
Guide user through problem-solution framing:
PROBLEM STATEMENT
=================
What problem does your project solve?
PROBLEM:
[User describes the pain point]
Good problem statements:
- "Small business owners spend 5+ hours/week on invoicing"
- "Developers waste time switching between 10+ tools"
- "Remote teams lose context in async communication"
WHO EXPERIENCES IT:
[Target user/segment]
IMPACT IF UNSOLVED:
[Business/personal cost of the problem]
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.
- 3d ago First seen · 336 lines · 48 tokens per session scan B 983c13ca4c2f
my_project is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 1,966 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
plan-new
Plan a complex project with discovery, structure, and kill criteria.
create-hook
Create a new custom automation hook.
remember
Explicitly save something to memory as an experience.
context-stats
Show context window usage, active tier, and system stats.