suxiaoqiang-cli: Instructions file for Codex

AGENTS.md

suxiaoqiang-cli AGENTS.md is an instructions file for Codex, OpenCode from AiGuangInc/suxiaoqiang-cli. It costs 402 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for publishing a command-line package to npm, the package registry for JavaScript and Node.js software.

In plain words
What is it for?
Use them when preparing a release pull request, updating version information and release notes, or investigating a failed automated npm publication.
Why use it?
They prevent release files from disagreeing and explain why publishing should happen through GitHub Actions rather than a developer’s local login. They also give checks for diagnosing npm service or authentication failures.

Instructions file for CodexOpenCode

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

This is AiGuangInc/suxiaoqiang-cli's own configuration. It tells Codex and OpenCode how to work on suxiaoqiang-cli 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 suxiaoqiang-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AiGuangInc/suxiaoqiang-cli. 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/AiGuangInc/suxiaoqiang-cli/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/AiGuangInc/suxiaoqiang-cli

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 suxiaoqiang-cli AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/aiguanginc/suxiaoqiang-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/aiguanginc/suxiaoqiang-cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 402 This file is loaded in full into every session.
When invoked 402 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 $0.00402 $0.00402
Opus 5.5 $0.00161 $0.00161
Sonnet 5.5 $0.00080 $0.00080
Haiku 4.5 $0.00040 $0.00040

Measured 15d ago against content hash 306448825ae6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

suxiaoqiang-cli 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 15d 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 · 30 lines

What it actually says

Repository working agreements

CLI publication

  • Publish through a release PR. Keep package.json, package-lock.json (including packages[""].version), and .github/release.json.version consistent, and include nonempty release notes. Merging the PR into main with a change to .github/release.json triggers .github/workflows/publish-npm.yml.
  • GitHub Actions owns npm publication through trusted publishing in the npm-publish environment. Local npm login and local npm tokens are unrelated to this path; do not use local publication as a fallback.
  • Before changing authentication or release code, read the failing Actions step and its HTTP response. Check the npm service status at https://status.npmjs.org/ when registry requests fail or time out.
  • npm OIDC token exchange can return HTTP 503 during a service outage, after which npm reports ENEEDAUTH. That message alone does not prove that trusted publishing is misconfigured. Use the exchange response and Actions permissions as evidence; enable verbose logging for diagnosis only when needed.
  • For an upstream outage, report the cause, wait for recovery, then rerun the original failed Actions job after checking whether the version is already published. Keep the normal release workflow simple: do not add incident-specific retry loops, compatibility branches, temporary release entry points, or permanent verbose logging. Do not refresh local credentials for an Actions failure.
  • Preserve existing release tags and published package contents. Package fixes require a new version and release PR; never move a release tag to retry.
  • A successful publish command is not full acceptance. Verify the exact version from the public npm registry, install it in isolation, exercise the changed behavior through sxq, and clean up acceptance fixtures. Publish and verify both documentation sites after package acceptance.
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. 15d ago First seen · 30 lines · 402 tokens per session scan A 306448825ae6

Subscribe to this mod's changes

suxiaoqiang-cli AGENTS.md is an instructions file published in the GitHub repository AiGuangInc/suxiaoqiang-cli (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 402 tokens to every session, about $0.0016 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 2026-10-22.

Related

suxiaoqiang-cli AGENTS.md compared with instructions from other repositories

suxiaoqiang-cli AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
suxiaoqiang-cli AGENTS.mdAiGuangInc/suxiaoqiang-cliInstructions file57d agoApache-2.0A402Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode