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 instructions/thiago-ss/pi-agent-config/agents-mdgit clone --depth 1 https://github.com/thiago-ss/pi-agent-configWrote 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/instructions/thiago-ss/pi-agent-config/agents-md)<a href="https://agentmods.dev/instructions/thiago-ss/pi-agent-config/agents-md"><img src="https://agentmods.dev/badge/instructions/thiago-ss/pi-agent-config/agents-md.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 | $0.00511 | $0.00511 |
| Opus 5 | $0.00255 | $0.00255 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
pi-agent-config AGENTS.md 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 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.
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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pi agent instructions
Keep this file short.
General
- Prefer small, targeted changes.
- Use
readto inspect files andeditfor precise replacements. - Use
writeonly for new files or full rewrites. - Do not modify
auth.jsonunless explicitly asked.
Workflow selection
- Think first: choose the lightest process that fits the task.
- Use GSD for broad, multi-step, uncertain, or high-risk work.
- If GSD fits, use the appropriate
/gsd-*flow; prefer the smallest useful one. - For new or non-trivial project work in Pi, default to the Agent Skills flow:
using-agent-skills→spec-driven-development→planning-and-task-breakdown→incremental-implementation→test-driven-development(thencode-review-and-qualitybefore merge). - Shortcut mapping:
/spec= spec-driven-development,/plan= planning-and-task-breakdown,/build= incremental-implementation,/test= test-driven-development,/review= code-review-and-quality,/ship= shipping-and-launch. - If GSD does not fit, use mini-RPI: research → plan → implement.
Architecture
- Follow SOLID.
- Favor separation of concerns, clear boundaries, and reusable abstractions.
- Extract reusable code; avoid duplication, god objects, and tangled logic.
- Prefer composition, small functions, and explicit interfaces.
Pi-specific work
- When working on Pi internals, read the Pi docs first:
~/.nvm/versions/node/v25.8.0/lib/node_modules/@mariozechner/pi-coding-agent/README.md- and the relevant files in
.../docs/
- Follow any linked
.mdfiles before implementing changes. - Validate TypeScript changes by loading them with Pi's Jiti/runtime when practical.
Local config areas
~/.pi/agent/extensions/for extensions~/.pi/agent/themes/for themes~/.pi/agent/settings.jsonfor agent settings
Extension notes
- Keep footer/UI changes consistent with the current theme and the user's requested density.
- If removing metrics or UI elements, also remove related shortcuts/help text and unused code paths.
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 · 44 lines · 511 tokens per session scan A 0a3bd8c3b772
pi-agent-config AGENTS.md is an instructions file published in the GitHub repository thiago-ss/pi-agent-config (2 stars, last pushed 4mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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 instructions, from other repositories
pi-tools AGENTS.md
AGENTS.md instructions for joelhooks/pi-tools: This repo uses pi-notes for durable project memory and local review surfaces.
pi-tools CLAUDE.md
Claude Code instructions for joelhooks/pi-tools: This repo has pi-notes installed. Use the repo Brain as the durable source of project knowledge.
pi-anthropic-auth AGENTS.md
AGENTS.md instructions for gotgenes/pi-anthropic-auth, covering agents guide: pi-anthropic-auth, project, primary goal, current status and principles.
pi-fabric AGENTS.md
AGENTS.md instructions for monotykamary/pi-fabric, covering agents.md, golden rule: build when done, before committing, incremental checks while iterating and package manager.
pi-agent-browser-native AGENTS.md
AGENTS.md instructions for fitchmultz/pi-agent-browser-native, covering pi-agent-browser-native, product-specific guidance, documentation placement, upstream capability baseline and command reference and tool result categories.
supi CLAUDE.md
Claude Code instructions for mrclrchtr/supi, covering claude.md, development status, pi docs-first rule, documentation expectations and package layout convention.