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/kunchenguid/gh-axi/agents-mdgit clone --depth 1 https://github.com/kunchenguid/gh-axiWrote 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/kunchenguid/gh-axi/agents-md)<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="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 5.1 | $0.03787 | $0.03787 |
| Opus 5 | $0.01894 | $0.01894 |
| Sonnet 5 | $0.00757 | $0.00757 |
| Haiku 4.5 | $0.00379 | $0.00379 |
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 yesterday.
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 — 121 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.
- Add durable project-specific notes here as they are discovered through real work.
Dependency bumps and the lockfile
The committed pnpm-lock.yaml is Prettier-formatted (multi-line resolution: and engines: blocks), which is not pnpm's native output format.
A plain pnpm install rewrites those blocks inline and produces a ~1000-line cosmetic churn even when only one dependency actually changed.
After bumping a dependency, run pnpm exec prettier --write pnpm-lock.yaml so the diff collapses to just the real change.
CI uses pnpm install --frozen-lockfile, which parses the YAML structurally and accepts the Prettier-formatted lockfile, so the formatting does not break the frozen-install check.
The SDK-provided update command
gh-axi runs its CLI through runAxiCli from axi-sdk-js (src/cli.ts) and registers no update command of its own.
Since [email protected] ships update as a RESERVED_COMMANDS built-in, gh-axi inherits gh-axi update for free, and the SDK auto-resolves the npm package name (gh-axi) by walking up to the nearest package.json.
The SDK also appends a "built-in": section to the top-level --help output at runtime, so src/cli.ts's TOP_HELP constant is a prefix of the rendered help rather than the whole thing.
Release process
Releases are cut by release-please from conventional commit messages on main; merging the bot's release PR triggers npm publish via .github/workflows/release-please.yml.
Do not hand-edit CHANGELOG.md or .release-please-manifest.json (a guard workflow blocks PRs that touch them), and regenerate skills/gh-axi/SKILL.md with pnpm run build:skill instead of editing it directly.
Every pull_request workflow (ci.yml, guard-generated-files.yml, no-mistakes-required.yml) uses paths-ignore for the release-please output set (.release-please-manifest.json, CHANGELOG.md, package.json) so release PRs create zero runs. Job-level bot ifs stay as defense in depth. test/release-ci-exclusions.test.ts derives that set from release-please-config.json and fails if a workflow drifts; update the ignore lists when adding extra-files or changing release-type.
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.
- yesterday Changed · +14 lines · +487 tokens per session 9e9bd42206b1
- 5d ago First seen · 107 lines · 3,300 tokens per session scan A 8db08a74531a
gh-axi AGENTS.md is an instructions file published in the GitHub repository kunchenguid/gh-axi (276 stars, last pushed 2d ago), licensed MIT. It adds 3,787 tokens to every session, about $0.0189 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 2026-08-30.
Other instructions, from other repositories
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
ai-usagebar CLAUDE.md
Claude Code instructions for akitaonrails/ai-usagebar, covering claude.md, release checklist — must do all of these, hard invariants — never break these, secret-discipline rules (learned the hard way) and live api smoke discipline.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
yandex360-mcp CLAUDE.md
Claude Code instructions for pa1ch/yandex360-mcp, covering claude.md — гайд для ассистента, как устроен релиз (всё автоматически по тегу), процедура релиза (шаги ассистента), гарды and архитектура (кратко).