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/boldblackai/harness/pigit clone --depth 1 https://github.com/boldblackai/harnessWhat 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 | $0.00459 |
| Opus 5 | $0.00000 | $0.00230 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
pi 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.
What it actually says
pi (default agent)
pi is the default agent. It supports many cloud providers and works with LM Studio locally.
Local mode
Pi defaults to LM Studio with google/gemma-4-e4b (16k context is sufficient):
npx @boldblackai/harness -p "write a fizzbuzz in Go"
You can specify a different local model with -m. HuggingFace-style names with slashes work correctly:
npx @boldblackai/harness -m "qwen/qwen3.5-9b" -p "write a fizzbuzz in Go"
Cloud mode
Pass an --env-file containing any supported API key:
| Provider | Environment Variable |
|---|---|
| Anthropic | ANTHROPIC_API_KEY |
| OpenRouter | OPENROUTER_API_KEY |
| OpenAI | OPENAI_API_KEY |
| Google Gemini | GEMINI_API_KEY |
| Mistral | MISTRAL_API_KEY |
| Groq | GROQ_API_KEY |
| Cerebras | CEREBRAS_API_KEY |
| xAI | XAI_API_KEY |
| Hugging Face | HF_TOKEN |
See the full provider list for more options.
Examples
# One-shot prompt
npx @boldblackai/harness -p "add a login endpoint"
# With a specific model
npx @boldblackai/harness -m anthropic/claude-sonnet-4-5 -p "refactor auth"
# Interactive session (no -p)
npx @boldblackai/harness
The -m flag is passed directly to pi as --model.
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 · 55 lines · 0 tokens per session scan A b780a608a44a
pi is an agent published in the GitHub repository boldblackai/harness (10 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 459 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 2026-08-31.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
kimi
Kimi CLI is Moonshot's coding agent. In CCR it is CLI only and always uses Only opened from CCR.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…