goal
Autonomous Opus loop that pursues a SPEC across multiple turns until every completion condition is satisfied or a real blocker surfaces.
Skill by waitdeadai
Chalk Labs
Need help deploying goal?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/waitdeadai-goal
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/goal
What's inside
- Skill name
goal- Description
- Autonomous Opus loop that pursues a SPEC across multiple turns until every completion condition is satisfied or a real blocker surfaces. Use only when the work is non-decomposable and benefits from sustained reasoning. Always preceded by /spec.
- License
- Apache-2.0
- Instructions
- 31 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /goal — autonomous goal loop Hand the SPEC to an Opus driver that works across many turns until every completion condition is met. Inspired by Claude Code 2.1.139's `/goal` semantics; sharpened by claudemax's spec-first gate and supervisor verification. ## Pre-requisites 1. `SPEC.md` exists at the project root. 2. Every completion condition has a verifyHint a blind reviewer could check. 3. The user understands this may run for many turns and incur significant Opus cost. ## Loop behavior - After every meaningful change, the driver re-evaluates the completion conditions. - When all are met, it emits a `FINISHED` block with per-condition evidence and exits. - When it cannot proceed (missing credential, ambiguous requirement, irreversible decision), it emits `BLOCKED` with what would unblock. - It does not invent success. If verifyHints don't pass a blind check, the driver iterates. ## Out of scope for /goal - Anything not in the SPEC. Even if the driver notices a broken adjacent thing, it logs it and stays in scope. - Cost downgrades. `/goal` is always Opus. If you need cheap, decompose into `/dispatch`-able packets first. ## Output A status (`finished | blocked | max-turns`), an evidence map keyed by completion condition id, a summary paragraph, and a session id for resumption. ## Always followed by /verify Never declare success on the strength of `/goal`'s own claim. `/verify` runs an independent Opus pass.
From waitdeadai/claudemax, Apache-2.0.
More from waitdeadai/claudemax
- 0.497score
orchestrate
waitdeadai
Multi-goal harness — runs N `/cmax` pipelines in parallel for DIFFERENT goals at the same time.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
cmax
waitdeadai
The default FAT umbrella.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
council
waitdeadai
3-Opus adversarial debate (proposer / critic / judge) for architectural decisions.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
deepresearch
waitdeadai
Iterative web-current research with source ledger.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
hive
waitdeadai
Same problem given to N agents in parallel; merge proposals.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
investigate
waitdeadai
Multi-source root-cause analysis for a specific bug or failure.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
mega
waitdeadai
Session-limit-aware mega-build orchestrator.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
introspect
waitdeadai
Confidence/assumption hard-gate before /goal handoff.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
opusolo
waitdeadai
Max-effectiveness umbrella.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
align
waitdeadai
One-shot semantic decision recorder.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
deepretaste
waitdeadai
Drift detection.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
harness-audit
waitdeadai
Periodic review of claudemax's own scaffolding against the current Opus capability.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- May 20, 2026 (5 months ago)
- Last release
- May 20, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/waitdeadai/claudemax
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from waitdeadai
- 0.497score
deepresearch
waitdeadai
Iterative web-current research with source ledger.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
investigate
waitdeadai
Multi-source root-cause analysis for a specific bug or failure.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
cmax
waitdeadai
The default FAT umbrella.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
council
waitdeadai
3-Opus adversarial debate (proposer / critic / judge) for architectural decisions.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
hive
waitdeadai
Same problem given to N agents in parallel; merge proposals.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
mega
waitdeadai
Session-limit-aware mega-build orchestrator.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get goal running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
goal skill. Agent Mart. https://agentmart.dev/skills/waitdeadai-goal (last updated 2026-10-24)