goal-prompt

An agent skill by trailofbits, from trailofbits/skills. Tags: automation, brainstorming, copy-editing, documentation, strategy.

What it does

Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress, clean up, or prepare a goal prompt, goal condition, /goal command, goal-mode objective, or copy-ready long-running task objective.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add trailofbits/skills --skill goal-prompt

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/trailofbits/skills
cp -r skills/plugins/goal-prompt/skills/goal-prompt ~/.claude/skills/goal-prompt

Safety box score

Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a local text formatter for `/goal` commands. It does not contact the network, write files, or need elevated privileges; the main thing it touches is whatever input file or stdin you point it at, which it reads and normalizes into output text.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It ships a runnable Python script (`scripts/format_goal_prompt.py`, `#!/usr/bin/env python3`) and tests, but the code only parses text and prints to stdout.
Network access	0 (none)	No code or docs open sockets, fetch remote content, or send data off-machine.
Filesystem reach	1 (low)	`read_text(path)` accepts a path or stdin and reads the referenced file (`Path(path).read_text(...)`), but the skill does not write or delete files.
Secrets & credentials	0 (none)	There is no handling of tokens, keychains, `.env` files, browser sessions, or other credential stores.
Privilege & persistence	0 (none)	No sudo, service registration, global install, or shell/OS configuration changes are present.
Instruction hijack surface	0 (none)	The files do not tell the agent to ignore instructions, hide behavior, or follow remote prompts; they only describe prompt formatting rules.
Irreversible actions	0 (none)	The skill only formats a goal prompt; it does not itself push, publish, send messages, deploy, or delete anything.
Transparency	0 (none)	The repository contents are plain text Python/Markdown/YAML with no binaries, installers, or runtime-decoded payloads.

Before installing

Inspect `scripts/format_goal_prompt.py` to confirm the only side effect is reading a file/stdin and printing normalized text.
Run `scripts/test_format_goal_prompt.py` in a scratch environment if you want to verify the formatter behavior before use.
If you will pass file paths to it, make sure you are comfortable with it reading any readable path you provide, not just files under the repo.

Rated 2026-10-20 by an automated review of 4 files from the skill's repository.

Source

Repository: trailofbits/skills (all skills from this repository)
Path: plugins/goal-prompt/skills/goal-prompt/SKILL.md
Branch: main
Collection: goal-prompt
Updated: 2026-09-19

brainstorm-experiments-existing — Design experiments to test assumptions for an existing product — prototypes, A/B tests, spikes, and other low-effort validation methods.
feature-forge — Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria.
grill-with-docs — A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
legacy-modernizer — Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps.
long-horizon-prompting — This skill should be used when writing, enhancing.
multi-agent-patterns — This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs.