Not in the top 1,000 by GitHub stars
robzilla1738/supergoal
Plan and autonomously build a software task end-to-end. One ready-to-paste /goal, adaptive phase count, memory preload + writeback, 3-strike self-healing recovery.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/supergoal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ec2f6eb8eb33 → ec2f6eb8eb33
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ec2f6eb8eb33
No earlier version was observed for comparison.
Verified commit ec2f6eb8eb3304a4ed32f1f18948a6c6198fcd67
git clone --filter=blob:none --no-checkout https://github.com/robzilla1738/supergoal.git .hotskills/robzilla1738-supergoal && git -C .hotskills/robzilla1738-supergoal checkout --detach ec2f6eb8eb3304a4ed32f1f18948a6c6198fcd67
# Copy each selected skill directory from .hotskills/robzilla1738-supergoal into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/robzilla1738/supergoal.git .hotskills/robzilla1738-supergoal && git -C .hotskills/robzilla1738-supergoal checkout --detach ec2f6eb8eb3304a4ed32f1f18948a6c6198fcd67
# Copy each selected skill directory from .hotskills/robzilla1738-supergoal into .agents/skills/<skill-name>/Heat
0.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- supergoal
skills/supergoal
How it works
supergoal
When your agent uses it
Plan and autonomously build a software task end-to-end. Triggered by `/supergoal`, "plan and ship X", "supercharged plan", "autonomous build", "plan it out and don't stop until it's done", "I don't want to babysit this", or any non-trivial feature/refactor/redesign the user wants driven to completion. Strongly prefer over a plain plan when the user signals "every aspect", "fully", "perfectly", "until done", or wants depth + autonomous follow-through. Recons the codebase, applies preloaded memory, researches best practices with whatever tools are available, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste `/goal` command — one paste between you and done — that drives the entire chain to completion with built-in retry, fix-spec recovery, and per-phase memory writeback. Works on Claude Code and Codex.
What it loads into context
Frontmatter
213 tokensAlways available to the agent
SKILL.md
9,898 tokensWhen the skill is activated
Reference documents
9,516 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What "every aspect is perfect" means here
- How this skill works (one-shot summary)
- Locate the skill directory
- Stage 0 — Available context (memory + tools)
- Stage 1 — Intake & clarifying questions
- Stage 2 — Recon (parallel)
- Stage 3 — Deep think
- Stage 4 — Decompose into phases
- Stage 5 — Write the roadmap and phase specs
- Stage 6 — Plan review & confirmation (hard gate)
- Stage 6.5 — Pre-flight smoke check
- Stage 7 — Hand off the `/goal` dispatch (one paste)
- Phase execution loop (inside the single `/goal` session)
- Memory writeback rules (referenced by PROTOCOL.md)
- Operating principles (read every run)
- When to deviate from the workflow
- Reference files
- Scripts
- Templates
Scripts executed separately
scripts/claim-run.shscripts/detect-env.shscripts/detect-stack.shscripts/repo-state.shscripts/summarize-repo.shscripts/validate-phase.sh
Files
../../.claude-plugin/marketplace.jsonasset542 bytes../../.claude-plugin/plugin.jsonasset542 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesSKILL.mdcore40,571 bytesreferences/goal-format.mddoc8,285 bytesreferences/phase-design.mddoc7,695 bytesreferences/planning-depth.mddoc3,312 bytesreferences/repo-state-comparison.mddoc5,609 bytesscripts/claim-run.shruns2,177 bytesscripts/detect-env.shruns1,227 bytesscripts/detect-stack.shruns4,466 bytesscripts/repo-state.shruns6,039 bytesscripts/summarize-repo.shruns3,376 bytesscripts/validate-phase.shruns1,451 bytestemplates/PROTOCOL.mddoc8,927 bytestemplates/ROADMAP.mddoc2,642 bytestemplates/STATE.mddoc1,476 bytestemplates/phase-goal.txtdoc1,543 bytes
Read SKILL.md
# Supergoal
You are running the Supergoal workflow. The user's task is:
$ARGUMENTS
Your job: **plan deeply, then auto-execute under a single `/goal`** until the task is verifiably complete across every phase.
## What "every aspect is perfect" means here
The user's bar is high. Translate it into measurable criteria, not vibes:
- **Functional** — the feature works for the golden path and the obvious edge cases
- **Engineering** — build, typecheck, lint, tests all pass; no new warningsView the complete source on GitHubSkills included
- supergoal
Repository facts
- License
- MIT
- Created
- May 12, 2026
- Last pushed
- Aug 18, 2026
- Forks
- 50
- Open issues
- 1
- Project activity
- Slowing
Rank over the last 12 weeks
Now #872 · best #709 · down 32 in 30 days
- #836 on Oct 6
- #870 on Oct 7
- #910 on Oct 8
- #858 on Oct 11
- #908 on Oct 16
- #872 since Oct 24
15 earlier periods
- #818 on Aug 1
- #709 on Aug 4
- #738 on Aug 10
- #749 on Aug 13
- #801 on Aug 25
- #779 on Aug 26
- #821 on Sep 1
- #796 on Sep 2
- #808 on Sep 3
- #816 on Sep 9
- #822 on Sep 10
- #834 on Sep 17
- #812 on Sep 20
- #840 on Sep 23
- #884 on Sep 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 14 notes
skills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/supergoal/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 6 network referencesin 2 files: .claude-plugin/marketplace.json:4 supergoal/references/phase-design.md:103
- No hidden or obfuscated text
- No instruction overrides
- 6 executable scriptsin 6 files: supergoal/scripts/claim-run.sh:1 supergoal/scripts/detect-env.sh:1 supergoal/scripts/detect-stack.sh:1 and 3 more
- No access to secrets
- No requests to vote in Hot
Show all 12 signals by file
.claude-plugin/marketplace.json
skills/supergoal/references/phase-design.md
- Network accessline 103
- **Diff snippets** — key changes inline, not full diffs - **Screenshots** — for UI phases, paths to screenshots saved during execution - **API responses** — `curl -X POST ... | jq` outputs for new endpoints - Network accessline 104
- **Screenshots** — for UI phases, paths to screenshots saved during execution - **API responses** — `curl -X POST ... | jq` outputs for new endpoints - **STATE.md update** — the new content of the phase's row - Network accessline 105
- **API responses** — `curl -X POST ... | jq` outputs for new endpoints
skills/supergoal/scripts/claim-run.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/supergoal/scripts/detect-env.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/supergoal/scripts/detect-stack.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/supergoal/scripts/repo-state.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/supergoal/scripts/summarize-repo.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/supergoal/scripts/validate-phase.sh
- Executable scriptline 1
#!/usr/bin/env bash
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 9 facts
- Network access in prose of documentationsupergoal/references/phase-design.md:103Low confidence
- Network access in prose of documentationsupergoal/references/phase-design.md:104Low confidence
- Network access in prose of documentationsupergoal/references/phase-design.md:105Low confidence
- Executable script in code of a file that runssupergoal/scripts/claim-run.sh:1High confidence
- Executable script in code of a file that runssupergoal/scripts/detect-env.sh:1High confidence
- Executable script in code of a file that runssupergoal/scripts/detect-stack.sh:1High confidence
- Executable script in code of a file that runssupergoal/scripts/repo-state.sh:1High confidence
- Executable script in code of a file that runssupergoal/scripts/summarize-repo.sh:1High confidence
- Executable script in code of a file that runssupergoal/scripts/validate-phase.sh:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/supergoal/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/supergoal/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/supergoal/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/supergoal/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.