What is Hipson AGENTS.md?

Project instructions for Hipson47/Hipson, including coding-agent behavior, repository workflows, and standards for planning, editing, and verification. They also describe when to use Hipson commands for routing or coordinating work.

Guiding ordinary coding and review tasks, including routing work, using Hermes when needed, keeping diffs small, and testing changes.

They give agents a consistent way to inspect a repository, choose a workflow, make focused changes, and run appropriate checks afterward.

How Hipson47/Hipson configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Hipson47/Hipson. 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/Hipson47/Hipson/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Hipson47/Hipson

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/hipson47/hipson/agents-md/github.svg)](https://agentmods.dev/instructions/hipson47/hipson/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hipson47/hipson/agents-md"><img src="https://agentmods.dev/badge/instructions/hipson47/hipson/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/hipson47/hipson/agents-md"><img src="https://agentmods.dev/badge/instructions/hipson47/hipson/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,276 This file is loaded in full into every session.

When invoked 1,276 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	$0.01276	$0.01276
Opus 5.5	$0.00510	$0.00510
Sonnet 5.5	$0.00255	$0.00255
Haiku 4.5	$0.00128	$0.00128

Measured 8d ago against content hash 7dba8d220e0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Hipson 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 8d 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 · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md instructions for Hipson

Senior software architect and coding agent.

Be concise, direct, practical. Informal chat ok. All code, docs, and comments in English.

First run: the user wants to use Hipson (not develop it)

This repository is Hipson itself. If the user cloned it to start using Hipson with their own projects:

Check hipson --version. If it is missing, install it: uv tool install hipson (from PyPI) or uv tool install . from this clone; uv itself: https://docs.astral.sh/uv/getting-started/installation/. Without uv: create a virtualenv and python -m pip install . (see docs/USAGE.md).
In the user's target project (a Git repository with at least one commit), run hipson init --client claude when Claude Code is the lead, or --client codex; preview with --dry-run and show the plan to the user before applying. Then the user restarts the client and approves the project MCP server hipson.
The lead workflow is in hipson --help (Lead quick reference) and docs/TASK_LEDGER.md: open a task with real acceptance checks (--check "pytest -q"), run workers through hipson task run, acknowledge results, close with hipson task close; hipson task do does all of it for one job.
To check this checkout itself: uv sync --all-extras then uv run python scripts/run_tests.py (about five minutes; uv run python -m pytest -q is equivalent).

Never write the user's real configs without showing the hipson init --dry-run plan first.

Lead and Worker Modes

Enter worker mode when the task brief says you are a worker for a lead, contains Worker rules:, or when HIPSON_ROLE=worker is set. A task or assignment id alone does not make you a worker. In worker mode, the lead is the control surface and owns orchestration and task-ledger updates (see docs/TASK_LEDGER.md). Work flat: do not spawn subagents; skip hipson work, hipson route, and the hipson contract show --json preflight; do not create progress or handoff notes (including docs/progress.md); do not commit or push; do not write the task ledger. Stay within the brief's scope, run the requested verification, and return the evidence it asks for. This rule takes precedence over the standalone workflow below; outside worker mode, keep the existing standalone behavior.

Read the full file on GitHub · 96 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.

8d ago Changed · -3 lines · -12 tokens per session 7dba8d220e0c
10d ago Changed · +19 lines · +355 tokens per session 3555e7254f62
13d ago Changed · +12 lines · +189 tokens per session a91d6c9f94e0
2mo ago First seen · 68 lines · 744 tokens per session scan A cb13669da400

Subscribe to this mod's changes

Hipson AGENTS.md is an instructions file published in the GitHub repository Hipson47/Hipson (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,276 tokens to every session, about $0.0051 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 2026-08-31.

agentic-workflow ai-agents cli codex codex-cli developer-tools

Hipson AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Hipson AGENTS.mdHipson47/Hipson	Instructions file	4	4d ago	Apache-2.0	A	1,276	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

Hipson: Instructions file for Codex