goal-prep

goal-prep is a skill for Claude Code from bonfire-systems/goalkeeper. It costs 68 tokens per session (1,225 once invoked), scanned A, original, MIT.

An interactive planning tool that turns a rough software idea into a written contract for completing the work.

In plain words
What is it for?
Use it to inspect a repository and draft a contract for a new coding task, including its proposed name and project-specific checks.
Why use it?
It removes ambiguity by defining the objective, completion conditions, validation command, and work that is out of scope before implementation begins.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the goalkeeper plugin — 8 skills, 1 hook shipped together

Good fit Use it to inspect a repository and draft a contract for a new coding task, including its proposed name and project-specific checks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add bonfire-systems/goalkeeper
Claude Code
/plugin install goalkeeper

Made for: Claude Code.

Or install goalkeeper, the plugin that ships this one along with the rest of its 8 skills, 1 hook.

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 goal-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-prep.svg)](https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-prep)
Your own site
<a href="https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-prep"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-prep.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00068 $0.01225
Opus 5 $0.00034 $0.00613
Sonnet 5 $0.00014 $0.00245
Haiku 4.5 $0.00007 $0.00122

Measured 8d ago against content hash 7fdc7219ff39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

goal-prep 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 8d 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/goal-prep/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are operating the goal-prep skill. Your job is to turn a rough idea into a precise, executable goalkeeper contract. A bad contract is goalkeeper's #1 failure mode — your work here is the highest-leverage step in the whole flow.

Inputs

  • args (rough idea, may be empty)
  • The current repo (you can read code, configs, docs)

Flow

1. Reconnaissance (read-only)

Before drafting anything, briefly survey the repo to ground the contract in reality:

  • Detect language/framework: package.json, pyproject.toml, Cargo.toml, go.mod, *.csproj, etc.
  • Find the test/lint/build commands the project actually uses (CI workflow files, Makefile, package.json scripts).
  • Skim the README and any AGENTS.md / CLAUDE.md for project conventions.
  • If the rough idea points to specific files or features, locate them.

Spend ~2–5 read-only tool calls here. Do not edit anything.

2. Draft the contract via interactive Q&A

Use AskUserQuestion to collect each field. Pre-fill recommendations from your recon so the user only has to confirm or redirect. Ask in this order:

  1. Slug — propose a kebab-case slug; let user confirm or rename.
  2. Objective — one sentence. If the rough idea is already crisp, just confirm. If vague, propose 2–3 sharper rewrites.
  3. Non-goals — propose 2–4 things explicitly out of scope based on the recon (e.g. "don't change CI", "don't refactor src/"). Multi-select with edit.
  4. Definition of Done — propose 3–6 measurable criteria. Mix qualitative ("no test files contain jest.") with quantitative ("≥20% test runtime improvement"). Multi-select with edit. DoD is what the judge checks — be specific, no fluff.
  5. Validator command — propose the most relevant command(s) you found in recon (e.g. pnpm test && pnpm lint). Confirm or override.
  6. Checkpoint cadence — propose default (every 5 file edits OR every 20 minutes). Confirm or override.
  7. Max rejections — default 5. Confirm or override.
  8. Judge mode — default subagent. Offer inline only if user explicitly wants cheaper iteration (note: inline is advisory only, not gate-grade).
  9. Wakeup seconds — only ask if validator is unusually fast or slow. Otherwise let goal skill pick cache-aware default.

Read the full file on GitHub · 75 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. 8d ago First seen · 75 lines · 68 tokens per session scan A 7fdc7219ff39

Subscribe to this mod's changes

goal-prep is a skill published in the GitHub repository bonfire-systems/goalkeeper (12 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 1,225 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens

hive.pdf

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…

aden-hive/hive · 98 tokens

hive.note-taking

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

aden-hive/hive · 30 tokens

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens