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/ihorkatkov/pantheonWrote 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/ihorkatkov/pantheon/setup-repo)<a href="https://agentmods.dev/commands/ihorkatkov/pantheon/setup-repo"><img src="https://agentmods.dev/badge/commands/ihorkatkov/pantheon/setup-repo.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 | $0.00014 | $0.00965 |
| Opus 5 | $0.00007 | $0.00483 |
| Sonnet 5 | $0.00003 | $0.00193 |
| Haiku 4.5 | $0.00001 | $0.00097 |
Grade A, and why
setup-repo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup-repo
Your job: inspect the product repository and fill the Project Configuration section of AGENTS.md.
The AGENTS.md file already exists at the workspace root ($PANTHEON_ROOT/AGENTS.md or ../../AGENTS.md). It has agent tables at the top (DO NOT TOUCH) and a Project Configuration section marked by HTML comments. You replace ONLY the content between <!-- PROJECT_CONFIG_START --> and <!-- PROJECT_CONFIG_END -->.
Hard Rules
- Do NOT run any install, build, or test commands (
npm install,mix deps.get,pip install,cargo build, etc.) - Do NOT modify any files in the product repository
- Do NOT modify any content above
<!-- PROJECT_CONFIG_START --> - Do NOT remove the
<!-- PROJECT_CONFIG_START -->or<!-- PROJECT_CONFIG_END -->markers - You READ the repo, then UPDATE one section of one file. Nothing else.
Step 1: Inspect the Repo
Read configuration files to identify the stack (do NOT execute anything):
package.json,deno.json,tsconfig.json→ Node.js / Deno / TypeScriptCargo.toml→ Rustgo.mod→ Gopyproject.toml,setup.py,requirements.txt→ Pythonmix.exs→ ElixirGemfile→ Rubypom.xml,build.gradle→ JavaMakefile,Justfile→ Build system.github/workflows/,.gitlab-ci.yml,.circleci/→ CI/CD
Then read:
- 3-5 source files for import/naming patterns
- 3-5 test files for test framework and patterns
- Formatter/linter configs
git log --oneline -20for commit conventions
Step 2: Write the Project Configuration
Read the existing $PANTHEON_ROOT/AGENTS.md (or ../../AGENTS.md). Find the <!-- PROJECT_CONFIG_START --> marker. Replace everything from that marker through <!-- PROJECT_CONFIG_END --> with:
<!-- PROJECT_CONFIG_START -->
## Project Configuration
### Validation
\`\`\`bash
[THE primary command to run before committing — e.g., mix precommit, npm run lint && npm test, cargo clippy && cargo test]
\`\`\`
Agents MUST run this before committing any changes.
### Testing
\`\`\`bash
# Run all tests
[command]
# Run a single test file
[command path/to/test]
# Run a specific test
[command with filter/line number]
\`\`\`
- **Framework**: [name]
- **Test file naming**: [pattern]
- **Test helpers/setup**: [what's available]
### Linting & Formatting
\`\`\`bash
# Format code
[command]
# Check formatting
[command]
# Lint / compile check
[command]
\`\`\`
### Development
\`\`\`bash
# Start dev server
[command]
# Database setup/migration
[command]
# Install dependencies
[command]
\`\`\`
### Repository Structure
\`\`\`
[directory tree with one-line descriptions]
\`\`\`
### Code Style
- **Formatting**: [tabs/spaces, width, key rules]
- **Imports**: [patterns with examples from the repo]
- **Naming**: [files, modules, functions, variables]
- **Error handling**: [patterns observed]
### Git Conventions
- **Branches**: [pattern]
- **Commits**: [pattern from git log]
### Critical Rules
1. Ask for clarification rather than making assumptions
2. Make smallest reasonable changes — don't refactor unrelated code
3. All changes need tests
[ADD: 3-10 project-specific rules discovered from the codebase]
<!-- PROJECT_CONFIG_END -->
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.
- 7d ago First seen · 126 lines · 14 tokens per session scan A 434b6624f24f
setup-repo is a command published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 965 once invoked, about $0.0001 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.