skillcaddy: Instructions file for Codex

AGENTS.md

skillcaddy AGENTS.md is an instructions file for Codex, OpenCode from chenweil/skillcaddy. It costs 920 tokens per session, scanned A, original, MIT.

Project instructions for the skillcaddy codebase, covering agent skills, GitHub Issues, triage labels, and domain documentation. Triage means sorting and labeling work so it can be handled by the right role or workflow.

In plain words
What is it for?
Use it when working on skillcaddy, especially to manage GitHub Issues, apply triage labels, or consult the repository's context and architecture decisions.
Why use it?
It gives the agent the repository's expected process for tracking and classifying work. This reduces inconsistent issue handling and avoids missing project-specific guidance.

Instructions file for CodexOpenCode

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

This is chenweil/skillcaddy's own configuration. It tells Codex and OpenCode how to work on skillcaddy 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 skillcaddy configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/chenweilong/project/skillcaddy.

Reuse

Borrowing it

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

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 skillcaddy AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chenweil/skillcaddy/agents-md"><img src="https://agentmods.dev/badge/instructions/chenweil/skillcaddy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 920 This file is loaded in full into every session.
When invoked 920 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.00920 $0.00920
Opus 5.5 $0.00368 $0.00368
Sonnet 5.5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 5d ago against content hash a92ee29f8623, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skillcaddy AGENTS.md scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

with a cache-busting query string; a plain `curl` of the tarball URL may fail
AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DO NOT send optional commentary

Agent skills

Issue tracker

Issues and PRDs are tracked in GitHub Issues. See docs/agents/issue-tracker.md.

Triage labels

Use the default five-role triage vocabulary. See docs/agents/triage-labels.md.

Domain docs

This is a single-context repository with a root CONTEXT.md and system-wide ADRs under docs/adr/. See docs/agents/domain.md.

Releasing

Skillcaddy is distributed as the npm package skillcaddy and through the Homebrew tap chenweil/tap. The release order matters: commit and tag first, publish second, so the artifact on the registry is traceable to a commit.

1. Prepare the release

Bump package.json to the next version, move the ## [Unreleased] section of CHANGELOG.md into a ## [X.Y.Z] - <date> section, and commit:

git commit -am "chore(release): X.Y.Z"
git tag -a vX.Y.Z -m "Release X.Y.Z"

2. Publish to npm — the maintainer runs this, not the agent

The npm account binds two-factor authentication to a macOS passkey, so there is no TOTP code to request and npm publish --otp=... cannot work. npm publish prints a browser authentication URL and waits for the maintainer to approve it with Touch ID:

cd /Users/chenweilong/project/skillcaddy && npm publish

An agent must not ask the maintainer for a six-digit code: there is none. Ask the maintainer to run the command, then continue with step 3.

Two follow-ups belong to the same browser-authenticated step:

  • The publish flow first creates a placeholder version 0.0.0-stage. The maintainer removes it with npm unpublish [email protected].
  • Verify: npm view skillcaddy versions lists exactly the new version, and npx skillcaddy --version runs it.

3. Refresh the Homebrew formula and push the tap

Two commands, in this order:

bash scripts/update-homebrew-formula.sh   # version + sha256 in Formula/skillcaddy.rb
bash scripts/publish-homebrew-tap.sh      # refresh → brew style → copy into the tap → commit → push

Read the full file on GitHub · 93 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. 5d ago Changed · +77 lines · +820 tokens per session a92ee29f8623
  2. 1mo ago First seen · 16 lines · 100 tokens per session scan A efddb53e8531

Subscribe to this mod's changes

skillcaddy AGENTS.md is an instructions file published in the GitHub repository chenweil/skillcaddy (29 stars, last pushed 5d ago), licensed MIT. It adds 920 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories