What is skeeper AGENTS.md?

A contributor guide for compozy/skeeper that tells coding agents how to work in the repository. It covers required skills, project conventions, dependency changes, and verification commands.

Use it when modifying this project, particularly when writing Go code, debugging, adding tests, changing dependencies, or preparing a completed task.

It prevents common mistakes such as editing dependencies directly or skipping mandatory checks. It also makes the required process clear for Go code, tests, bug fixes, and integration work.

skeeper AGENTS.md — Instructions file by compozy

Install

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.

agentmods

npx agentmods add instructions/compozy/skeeper/agents-md

Clone the repo

git clone --depth 1 https://github.com/compozy/skeeper

Made for: Codex, OpenCode.

Per session 3,290 This file is loaded in full into every session.

When invoked 3,290 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.03290	$0.03290
Opus 5	$0.01645	$0.01645
Sonnet 5	$0.00658	$0.00658
Haiku 4.5	$0.00329	$0.00329

Measured 2d ago against content hash 1edb092b300c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skeeper 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skeeper CLAUDE.md — 100% identical, 0 lines differ

AGENTS.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides project guidance for coding agents working in this repository.

HIGH PRIORITY

IF YOU DON'T CHECK SKILLS your task will be invalidated and we will generate rework
YOU CAN ONLY finish a task if make verify passes at 100% (runs fmt + lint + test + build). No exceptions — failing any of these commands means the task is NOT COMPLETE
make lint has zero tolerance. Zero issues allowed — any golangci-lint issue is a blocking failure
ALWAYS check dependent package APIs before writing integration code or tests to avoid writing wrong code
NEVER use workarounds — always use the no-workarounds skill for any fix/debug task + testing-anti-patterns for tests
ALWAYS use the no-workarounds and systematic-debugging skills when fixing bugs or complex issues
NEVER use web search tools to search local project code — for local code, use Grep/Glob instead
YOU SHOULD NEVER add dependencies by hand in go.mod — always use go get instead

MANDATORY REQUIREMENTS

MUST run make verify before completing ANY subtask
ALWAYS USE the golang-pro skill before writing any Go code
ALWAYS USE the systematic-debugging + no-workarounds skills before fixing any bug
ALWAYS USE the testing-anti-patterns skill before writing or modifying tests
ALWAYS USE the verification-before-completion skill before claiming any task is done
Skipping any verification check will result in IMMEDIATE TASK REJECTION

Project Overview

skeeper is a single-binary Go command-line interface built with production-grade patterns and agent-ready tooling. The CLI is structured around cobra and exposes subcommands wired through internal/cli.

Toolchain pin: Go 1.26.2 (managed via mise.toml + .go-version), Bun 1.3.4 (.bun-version), golangci-lint v2.11.4, gotestsum v1.13.0, gopls/modernize v0.21.1, goreleaser v2.6.1. Run mise install to provision everything.

Read the full file on GitHub · 232 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.

2d ago First seen · 232 lines · 3,290 tokens per session scan A 1edb092b300c

Subscribe to this mod's changes

skeeper AGENTS.md is an instructions file published in the GitHub repository compozy/skeeper (85 stars, last pushed 3mo ago), licensed MIT. It adds 3,290 tokens to every session, about $0.0164 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.

Debugging Testing Writing and docs

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

skeeper AGENTS.md