Borrowing it
Nothing to install: this file belongs to cfpperche/picode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cfpperche/picode/main/AGENTS.mdgit clone --depth 1 https://github.com/cfpperche/picodeWrote 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/cfpperche/picode/agents-md)<a href="https://agentmods.dev/instructions/cfpperche/picode/agents-md"><img src="https://agentmods.dev/badge/instructions/cfpperche/picode/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/cfpperche/picode/agents-md"><img src="https://agentmods.dev/badge/instructions/cfpperche/picode/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03391 | $0.03391 |
| Opus 5.5 | $0.01356 | $0.01356 |
| Sonnet 5.5 | $0.00678 | $0.00678 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade A, and why
picode 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 1mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Operating contract for coding agents in this repository
Every agent CLI that reads
AGENTS.mdloads this file at session start. It is the source of truth for how agents operate here. Humans follow the same rules via CONTRIBUTING.md. The rules live here; their detail and history live indocs/agents/— open those files when a rule applies to what you are doing.
What PiCode is
PiCode is a browser-based Agent Development Environment (ADE) for coding-agent
CLIs. One Go binary serves a rich web UI that lets users create, configure
and orchestrate agents across multiple workspaces — including people who
avoid terminals entirely. The moat: users control their agents from the
moment of creation. Read README.md before substantial work;
docs/architecture.md is an index; the subsystem
files under docs/architecture/ are what the table below names.
An agent is a workspace or free instance of any launchable CLI — Pi,
Claude Code, Codex, Grok, Hermes Agent, OpenCode, Muse Code, Antigravity or
Omp (ADR-0160, ADR-0179). Only Pi has a managed mode (pi --mode rpc,
ADR-0091); every other CLI runs its own TUI in a PiCode terminal. Pi is one
CLI among nine, never a dependency: PiCode runs with none of them present,
and tmux is its only runtime requirement. Copy or code that presents Pi as
required, or PiCode as "for Pi", is a defect. Managed mode for the other CLIs
is future work, not a capability to infer from a terminal integration.
What to read for which change (ADR-0086)
Reading is a cost. Start from docs/handoff.md (make handoff renders it;
in flight, next up, debts) and this file; add only what the change needs:
| Change | Read before the first edit |
|---|---|
| CSS / copy / one component | .pi/skills/uiux-review/SKILL.md; the component and its CSS |
| New or redesigned surface | above + docs/benchmarks.md (UI/UX section) + the one docs/benchmarks/ note it adapts |
| Handler / store / RPC | the docs/architecture/<component>.md file; the ADRs its comments cite |
| Protocol, persistence, security model, process | the ADRs it touches (index in docs/decisions/README.md); docs/decisions/template.md |
Docs site (docs-site/) |
docs/guidelines.md |
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.
- 1mo ago Changed · +1 lines · +16 tokens per session 7fae8500daed
- 1mo ago Changed · -104 lines · -1,882 tokens per session 1b530c971a24
- 1mo ago Changed · +11 lines · +220 tokens per session aa23a9eb44c8
- 1mo ago Changed · +17 lines · +357 tokens per session ff7c126c9709
- 1mo ago Changed · +28 lines · +550 tokens per session d91566539307
- 1mo ago Changed · +3 lines · +58 tokens per session 0a246b755a96
- 1mo ago First seen · 260 lines · 4,072 tokens per session scan A 7738ab407c63
picode AGENTS.md is an instructions file published in the GitHub repository cfpperche/picode (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,391 tokens to every session, about $0.0136 per session on Opus 5.5. 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 2026-09-12.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.