goose-setup

A setup guide for adding persistent instructions to Goose, a command-line and desktop coding assistant, so the same guidance is loaded in every project and session.

In plain words
What is it for?
Use it to create the global instructions file and register it in Goose's configuration.
Why use it?
It prevents recurring instructions from being forgotten or copied manually between sessions.

Skill for Claude CodeCodex

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 skills/rhtevan/agentfs/goose-setup
Any agent
npx skills add rhtevan/agentfs --skill goose-setup
Clone the repo
git clone --depth 1 https://github.com/rhtevan/agentfs

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00016 $0.01127
Opus 5 $0.00008 $0.00563
Sonnet 5 $0.00003 $0.00225
Haiku 4.5 $0.00002 $0.00113

Measured 2d ago against content hash 91833b9724ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

goose-setup 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.

skills/goose-setup/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goose Global Setup

Configure Goose with persistent instructions that apply across all projects and sessions.

What It Does

  1. Creates a persistent instructions file at ~/.config/goose/instructions.md
  2. Registers it in ~/.config/goose/config.yaml via GOOSE_MOIM_MESSAGE_FILE
  3. Instructions are injected into Goose's working memory every turn, so they can never be forgotten

Prerequisites

  • Goose is installed and ~/.config/goose/config.yaml exists
  • Familiarity with Goose's persistent instructions feature

Note on Tool Discovery

Previous versions of this skill included "Tool Discovery" instructions to help Goose find devbox/Nix-installed tools at non-standard paths. This is no longer needed if you have configured the goose-shell wrapper (~/.local/bin/goose-shell) and set GOOSE_SHELL in the Goose Desktop .desktop file. The wrapper sources ~/.bashrc before executing commands, which sets up nix, devbox, crc/oc, sdkman, and all other PATH entries automatically — even for non-interactive shells.

See the related files:

  • ~/.local/bin/goose-shell — wrapper that sources ~/.bashrc
  • ~/.local/share/applications/Goose.desktop — passes GOOSE_SHELL to the Goose process
  • ~/.config/environment.d/60-goose-shell.conf — sets GOOSE_SHELL for systemd user session

Steps

Step 1: Create the instructions file

Create ~/.config/goose/instructions.md with your global instructions:

## Path Hygiene

- **Never use explicit home directory paths** like `/home/<user>/` in scripts, configurations, or output.
- Always use `~` or `$HOME` instead.
- When displaying paths to the user, prefer `~/...` over `/home/<user>/...`.

## Git Push Safety

Before any `git push`, follow these steps **in order**. Do NOT skip
any step, even if the user says "go ahead", "push it", or "yes".

1. **STOP** — do NOT push yet. The user's "go ahead" authorizes the
   *intent* to push, not the push itself. The preflight must run first.
2. **Scan** the commits to be pushed for:
   - Secrets, credentials, API keys, tokens, private keys
   - Hardcoded user paths (`/home/<user>/`, `/Users/<user>/`)
   - PII (personal emails, phone numbers, addresses)
   - Sensitive data (internal IPs, hostnames, URLs)
3. **Present** the evaluation report to the user in table format,
   with a clear CLEAN / ISSUES FOUND verdict.
4. **Wait** for explicit approval **after** the report is shown.
5. **Then** — and only then — execute `git push`.

Read the full file on GitHub · 124 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 124 lines · 16 tokens per session scan A 91833b9724ca

Subscribe to this mod's changes

goose-setup is a skill published in the GitHub repository rhtevan/agentfs (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,127 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens