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_setupgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWhat 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 | $0.00049 | $0.02031 |
| Opus 5 | $0.00024 | $0.01015 |
| Sonnet 5 | $0.00010 | $0.00406 |
| Haiku 4.5 | $0.00005 | $0.00203 |
Grade A, and why
my_setup 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 2d 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/my_setup - Claude Code Configuration
Create optimized CLAUDE.md and Claude Code configuration by combining project context (project.md), brand guidelines (brand.md), and technical codebase analysis.
Recommended Workflow
1. /my_project → Creates project.md (project brief)
2. /my_brand → Creates brand.md (brand guidelines)
3. /my_setup → Creates CLAUDE.md (technical config)
Arguments
- No arguments: Full setup workflow
--claude-md-only: Only create/update CLAUDE.md--rules-only: Only generate path-specific rules--full: Complete setup including rules and hooks
Workflow
Phase 1: Context Discovery
Check for existing project context:
# Check for project.md (project brief)
ls -la project.md PROJECT.md 2>/dev/null
# Check for brand.md (brand guidelines)
ls -la brand.md BRAND.md 2>/dev/null
# Check for existing CLAUDE.md
ls -la CLAUDE.md .claude.md .claude.local.md 2>/dev/null
# Check .claude directory
ls -la .claude/ 2>/dev/null
Present findings:
CONTEXT DISCOVERY
=================
Project Context:
- project.md: [Found / Not found]
- brand.md: [Found / Not found]
- CLAUDE.md: [Found / Not found]
[If project.md or brand.md missing:]
RECOMMENDATION:
For best results, create project.md and brand.md first:
1. Run /my_project - Define project identity and goals
2. Run /my_brand - Define brand guidelines
3. Then run /my_setup - Create CLAUDE.md
Continue anyway?
1. Yes, proceed with technical analysis only
2. Run /my_project first
3. Run /my_brand first
Phase 2: Extract Context
If project.md exists, extract:
- Project name and description
- Target audience (for tone calibration)
- Core features (for architecture context)
# Read project.md for context
cat project.md 2>/dev/null
If brand.md exists, extract:
- Brand archetype (for voice/tone)
- Color palette (for design rule generation)
- Typography (for style consistency)
# Read brand.md for context
cat brand.md 2>/dev/null
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.
- 2d ago First seen · 387 lines · 49 tokens per session scan A ce4fa717c029
my_setup is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 2,031 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 2026-08-31.
Other commands, from other repositories
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
create-hook
Create a new custom automation hook.
create-command
Create a new custom slash command.
instinct-import
Import instincts from external sources.
evolve
Analyze instincts and suggest or generate evolved structures.
model-config
View or change the primary model that handles your coding work across srooter (the gateway), the route-task hooks, and Maggy. One setting, read everywhere. Stored in /.claude/model-config.json.