Goal Chain
Runs judge-gated linear goal chains for Claude Code, but only as one piece of the goalkeeper plugin, not standalone.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · ea5d8a6
Manually executed the Start-mode file writes (chain.json/active.json/state.json/log.md) for a throwaway 2-goal chain and every field matched the documented canonical shapes exactly, but the skill hard-depends on the sibling goal-judge and goal-prep skills (and skills/goal/SKILL.md's 'Canonical state shapes' section) that live outside skills/goal-chain/ -- a bare copy of just that folder has no contract-creation step and no judge to hand off to.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 3/5
- Triggers reliably 5/5
- Output vs. baseline 6/10
- Docs & honesty 5/5
What Goal Chain does
Executes an ordered list of goalkeeper goals one after another, spawning a fresh-context executor subagent per goal and gating advancement on a separate judge subagent's approval against each goal's Definition of Done. Triggers on `/goal-chain "<file>"` to start a chain, and is auto-invoked by the goal-judge skill to advance the cursor after an approval.
How to install Goal Chain
git clone https://github.com/bonfire-systems/goalkeeper.git
mkdir -p ~/.claude/skills
cp -r goalkeeper/skills/goal-chain ~/.claude/skills/goal-chain
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Goal Chain
-
/goal-chainRuns judge-gated linear goal chains for Claude Code, but only as one piece of the goalkeeper plugin, not standalone.
It also activates on plain-language prompts like these:
-
Run this ordered list of goals one after another until they're all done -
Advance the goal cursor now that this step got judged and approved -
Kick off a linear multi-goal chain from my goals file and execute it
Frequently asked questions
- Is the Goal Chain skill free?
- Yes. The skill itself is free from bonfire-systems/goalkeeper. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Goal Chain work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Manually executed the Start-mode file writes (chain.json/active.json/state.json/log.md) for a throwaway 2-goal chain and every field matched the documented canonical shapes exactly, but the skill hard-depends on the sibling goal-judge and goal-prep skills (and skills/goal/SKILL.md's 'Canonical state shapes' section) that live outside skills/goal-chain/ -- a bare copy of just that folder has no contract-creation step and no judge to hand off to.
- What is the Goal Chain SkillProof Score?
- 7.6/10 — installs cleanly 3/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.
- How do I install Goal Chain?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Goal Chain with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.