agentmods.dev

gh-axi: Instructions file for Codex

AGENTS.md

gh-axi AGENTS.md is an instructions file for Codex, OpenCode from kunchenguid/gh-axi. It costs 1,057 tokens per session, scanned A, original, MIT.

Repository-specific instructions for gh-axi, a command-line tool that uses the Axi software development kit.

In plain words
What is it for?
They guide dependency bumps, frozen-lockfile checks, use of the SDK-provided update command, releases, and changes to the installable skill.
Why use it?
They document project memory, dependency-update details, lockfile formatting, and the release process, reducing maintenance errors.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is kunchenguid/gh-axi's own configuration. It tells Codex and OpenCode how to work on gh-axi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gh-axi configures →

not rated 347repo +6 changed 29d ago A scan 1,057 tokens original MIT
View source ↗ kunchenguid/gh-axi
Reuse

Borrowing it

Nothing to install: this file belongs to kunchenguid/gh-axi. 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/kunchenguid/gh-axi/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kunchenguid/gh-axi

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.

agentmods badge for gh-axi AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kunchenguid/gh-axi/agents-md/github.svg)](https://agentmods.dev/instructions/kunchenguid/gh-axi/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kunchenguid/gh-axi/agents-md"><img src="https://agentmods.dev/badge/instructions/kunchenguid/gh-axi/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.

agentmods 80×15 button for gh-axi AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kunchenguid/gh-axi/agents-md"><img src="https://agentmods.dev/badge/instructions/kunchenguid/gh-axi/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,057 This file is loaded in full into every session.
When invoked 1,057 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01057 $0.01057
Opus 5.5 $0.00423 $0.00423
Sonnet 5.5 $0.00211 $0.00211
Haiku 4.5 $0.00106 $0.00106

Measured 29d ago against content hash 6136446b78e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gh-axi 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 29d 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 · 44 lines

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.

Project agent memory

This file is the project's committed home for project-intrinsic agent knowledge: build, test, release, architecture, and sharp-edge notes that should travel with the code.

Command behavior is owned by README.md. Contributor workflow, release-please, generated files, and implementation invariants are owned by CONTRIBUTING.md. Follow the section named below instead of restating it here.

  • VISION.md is the product scope: parity with gh through an AXI interface, and no GitHub capability that gh cannot provide.
  • The installable skill stays a stub that defers to the CLI. Never restate CLI-owned instructions in src/skill.ts or skills/gh-axi/SKILL.md (README Development).
  • gh-axi update is the SDK built-in, not a local command. TOP_HELP in src/cli.ts is only a prefix of rendered --help (README Development).
  • --hostname comes after the command and wins over GH_HOST. Set GH_HOST for the child only when the flag is present. resolveHost() is the host used when building or parsing URLs (README Global flags).
  • Secret values never appear in argv, stdout, or error text. secret set is stdin-only, rejects --body/-b, and throws on an interactive TTY instead of waiting. Unknown secret flags are echoed by name only. secret list and variable list have no --limit. Variable values are not secrets (README Usage).
  • A malformed or unsupported secret scope is rejected, never silently falls back to repository scope (README Usage).
  • Do not pass a RepoContext into ghJson from gist or project. gh project is owner-scoped: --owner defaults to the repo owner, else @me (CONTRIBUTING.md Implementation invariants).
  • Every *_FLAGS entry must appear in the matching flags{<sub>}: help section. Matching is whole-token. UNDOCUMENTED_ON_PURPOSE is only for a flag that always fails. Mark a repeatable flag (repeatable) in help.
  • Repeatable flags must use getAllFlags or takeAllFlags. getFlag and takeFlag keep only the first value. Reject a dangling or blank value.
  • Mirror gh's mutually exclusive pr merge switches locally, on the raw argv, before any gh call. Reject --flag=value on boolean merge switches the same way.
  • mapGhError returns on the first matching pattern, so a narrower pattern must sit ahead of a broader one.
  • src/version.ts imports Node builtins only. Do not add a wall-clock timing assertion to the version fast-path test. Do not rebuild the shared dist from an individual suite (README Development).
  • stack is a strict non-interactive adapter over github/gh-stack. Preserve stderr and the exact StackError exit code. Do not replace ghRaw with ghExec or mapGhError. Stack commands act only on the current working directory repo and never prompt (CONTRIBUTING.md Implementation invariants).
  • --attach requires gh >= 2.99.0. Live upload tests use GH_AXI_TEST_REPO set to a captain-owned test repo, never a product repo.

Read the full file on GitHub · 44 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.

  1. 29d ago Changed · -89 lines · -3,131 tokens per session 6136446b78e4
  2. 1mo ago Changed · +4 lines · +127 tokens per session e0c9df7772fe
  3. 1mo ago Changed · +8 lines · +274 tokens per session a21c148cc5aa
  4. 1mo ago Changed · +14 lines · +487 tokens per session 9e9bd42206b1
  5. 1mo ago First seen · 107 lines · 3,300 tokens per session scan A 8db08a74531a

Subscribe to this mod's changes

gh-axi AGENTS.md is an instructions file published in the GitHub repository kunchenguid/gh-axi (347 stars, last pushed today), licensed MIT. It adds 1,057 tokens to every session, about $0.0042 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 2026-08-30.

DevOps and cloudGit and workflowReleases
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens