gitdeck AGENTS.md

Project-specific instructions for developing debba/gitdeck, an open-source dashboard for GitHub, GitLab, and Forgejo.

In plain words
What is it for?
Use them when changing this project’s React and TypeScript code, adding features, writing tests, handling server-side Git access, or verifying builds.
Why use it?
They give coding agents consistent rules for architecture, tests, security, language, and required checks.

Instructions file for CodexOpenCode

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/debba/gitdeck/agents-md
Clone the repo
git clone --depth 1 https://github.com/debba/gitdeck

Made for: Codex, OpenCode.

Per session 173 This file is loaded in full into every session.
When invoked 173 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.

ModelPer sessionOnce invoked
Fable 5 $0.00173 $0.00173
Opus 5 $0.00086 $0.00086
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00017 $0.00017

Measured 2d ago against content hash b603dd9f3dae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gitdeck 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.

AGENTS.md · 12 lines

What it actually says

Agent Rules

  • Keep all code identifiers, comments, filenames, and documentation in English.
  • Preserve the current visual layout unless a task explicitly asks for UI changes.
  • Prefer React components for rendering and keep component files focused on one responsibility.
  • Put pure business logic in src/utils and cover it with unit tests under the mirrored tests/utils path.
  • Keep tests outside src; the tests folder must sit at the repository root and mirror the relevant src structure.
  • Do not mix unrelated refactors with feature work.
  • Use TypeScript for new source files unless an existing JavaScript integration requires otherwise.
  • Keep GitHub API and gh CLI access behind server-side endpoints; do not expose tokens to the browser.
  • Run npm test and npm run build after behavior changes when dependencies are available.
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. 2d ago First seen · 12 lines · 173 tokens per session scan A b603dd9f3dae

Subscribe to this mod's changes

gitdeck AGENTS.md is an instructions file published in the GitHub repository debba/gitdeck (399 stars, last pushed 11d ago), licensed MIT. It adds 173 tokens to every session, about $0.0009 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.