What is pincer AGENTS.md?

A repository instruction file for the Pincer project, documenting its architecture, coding conventions, development commands, and testing workflow.

It helps agents work on this Python project by describing how to install dependencies, run tests, lint code, format files, and understand the system.

It gives a coding agent project-specific guidance so its changes and commands match the repository's existing practices.

How pincerhq/pincer configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to pincerhq/pincer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pincerhq/pincer/dev/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/pincerhq/pincer

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pincerhq/pincer/agents-md/github.svg)](https://agentmods.dev/instructions/pincerhq/pincer/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/pincerhq/pincer/agents-md"><img src="https://agentmods.dev/badge/instructions/pincerhq/pincer/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pincerhq/pincer/agents-md"><img src="https://agentmods.dev/badge/instructions/pincerhq/pincer/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,475 This file is loaded in full into every session.

When invoked 2,475 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02475	$0.02475
Opus 5.5	$0.00990	$0.00990
Sonnet 5.5	$0.00495	$0.00495
Haiku 4.5	$0.00248	$0.00248

Measured 26d ago against content hash d670d266df99, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pincer 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 26d 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.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Project

Pincer (pincer-agent) is a self-hosted, security-first AI agent that operates across messaging channels (Telegram, WhatsApp, Discord, Slack, Signal, Email, Voice, Web) with 300+ native tools plus unlimited tools via MCP. Pure Python 3.14+ / asyncio — no agent framework (no LangChain, CrewAI, etc.), just provider SDKs (anthropic, openai) directly. The codebase is intentionally auditable. When building or extending LLM-facing functionality, prefer the latest Codex models and consult the Codex-api skill for current model IDs.

Commands

Use uv (preferred). Tests run from the repo root; pyproject.toml sets pythonpath = ["src"] and asyncio_mode = "auto".

uv sync --all-extras                 # install everything incl. dev + workspace MCP packages
uv run pytest                        # full suite
uv run pytest tests/test_agent.py    # one file
uv run pytest -k "test_approval" --no-cov   # by name filter
uv run pytest --cov=pincer --cov-report=term-missing

uv run ruff check .                  # lint
uv run ruff format .                 # format (CI fails on `ruff format --check .`)
uv run mypy src/                     # type check (strict)
uv run bandit -r src/pincer -ll -s B101,B104,B310,B608   # security scan

uv run pincer run                    # start agent (all configured channels)
uv run pincer doctor                 # 40+ config/security health checks

CI (.github/workflows/ci.yml) runs all of: pytest (incl. src/ms365-mcp/tests/), mypy on src/, ruff check, ruff format --check, and bandit. All must pass before merge.

Dashboard (React + Vite + TS in dashboard/, pnpm 10+): cd dashboard && pnpm install && pnpm dev (port 3000, proxies /api → :8080). CI runs pnpm type-check, pnpm lint, pnpm test.

Architecture

Agent loop — src/pincer/core/agent.py is the ReAct (reason+act) brain: receive message → load session + memories → call LLM with available tools → if tool_call, execute (in sandbox, with approval) → feed result back → repeat until text → deliver → persist session/memory/cost. This single loop is shared across every channel.

Read the full file on GitHub · 83 lines

Changes

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.

26d ago Changed · +2 lines · +170 tokens per session d670d266df99
1mo ago Changed · +16 lines · +647 tokens per session ca7dbdc0fe9a
1mo ago First seen · 65 lines · 1,658 tokens per session scan A 817fd9843e86

Subscribe to this mod's changes

pincer AGENTS.md is an instructions file published in the GitHub repository pincerhq/pincer (44 stars, last pushed yesterday), licensed MIT. It adds 2,475 tokens to every session, about $0.0099 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 2026-09-15.

Building agents

pincer AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pincer AGENTS.mdpincerhq/pincer	Instructions file	44	yesterday	MIT	A	2,475	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pincer: Instructions file for Codex