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 agents/andrewaltimit/template-repo/project-contextgit clone --depth 1 https://github.com/AndrewAltimit/template-repoWrote 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/agents/andrewaltimit/template-repo/project-context)<a href="https://agentmods.dev/agents/andrewaltimit/template-repo/project-context"><img src="https://agentmods.dev/badge/agents/andrewaltimit/template-repo/project-context.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 | $0.00000 | $0.01701 |
| Opus 5 | $0.00000 | $0.00851 |
| Sonnet 5 | $0.00000 | $0.00340 |
| Haiku 4.5 | $0.00000 | $0.00170 |
Grade B, and why
project-context 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- No `chmod 777` or overly permissive operations How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context for AI Code Review
Project Overview
This is a container-first, self-hosted project template maintained by a single developer (@AndrewAltimit). It uses Model Context Protocol (MCP) tools with zero-cost infrastructure.
AI Agent Ecosystem
This project uses six AI agents for development:
- Claude Code - Primary development assistant (architecture, implementation, docs)
- Codex - AI-powered code generation (OpenAI)
- OpenCode - Code generation via OpenRouter
- Crush - Code generation via OpenRouter
- Gemini CLI - Automated PR reviews (you are reviewing as Gemini)
- GitHub Copilot - Code review suggestions in pull requests
As the PR reviewer, focus on security, containers, and project standards.
Core Design Principles
1. Container-First Philosophy
- Everything runs in Docker containers except Gemini CLI (needs Docker access)
- No local dependencies required beyond Docker itself
- All Python CI/CD operations are containerized (ruff, pytest, bandit, etc.)
- The
automation-cliRust binary provides a unified interface to all CI stages
2. Self-Hosted Infrastructure
- All GitHub Actions run on self-hosted runners - no cloud costs
- Docker images are cached locally for fast builds
- Designed for individual developer efficiency - no team coordination needed
3. Architecture
- 18 Modular MCP Servers - Specialized servers for code quality, content creation, AI agents, etc.
- Python CI Container includes all development tools (Python 3.11)
- Docker Compose orchestrates all services
- No aggressive cleanup - Python cache prevention via environment variables
- Multi-stage CI/CD - format, lint-basic, lint-full, security, test stages
Review Focus Areas
PRIORITIZE reviewing
- Container configurations - Dockerfile correctness, security, user permissions
- Security concerns - No hardcoded secrets, no root containers, proper permissions
- Docker Compose changes - Service configs, port conflicts, volume mounts
- Script correctness - Shell scripts should use proper error handling (set -e)
- Python imports - Ensure compatibility with containerized environment
- MCP tool changes - Verify tools follow async patterns and error handling
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.
- 5d ago First seen · 198 lines · 0 tokens per session scan B 7cb6bfc3921e
project-context is an agent published in the GitHub repository AndrewAltimit/template-repo (131 stars, last pushed 2mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 1,701 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
creating-agents
Agents are created from templates or from scratch. Each agent runs as an isolated Docker container with its own filesystem, credentials, and MCP server configuration.
agent-session
Trinity has two conversation surfaces, and the difference is memory.
agent-files
Two-panel file manager in the Agent Detail Files tab for browsing, previewing, and editing agent workspace files.
agent-logs
View container logs for debugging and real-time telemetry metrics in the agent header.
agent-chat
The Chat tab in Agent Detail provides a bubble UI for conversing with agents, with persistent history and real-time status updates.
agent-system
An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.