Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add asteroid-belt/skulto --skill superbuildgit clone --depth 1 https://github.com/asteroid-belt/skultoWrote 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.
[](https://agentmods.dev/skills/asteroid-belt/skulto/superbuild)<a href="https://agentmods.dev/skills/asteroid-belt/skulto/superbuild"><img src="https://agentmods.dev/badge/skills/asteroid-belt/skulto/superbuild/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asteroid-belt/skulto/superbuild"><img src="https://agentmods.dev/badge/skills/asteroid-belt/skulto/superbuild.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 440 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 440 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.03672 |
| Opus 5 | $0.00026 | $0.01836 |
| Sonnet 5 | $0.00010 | $0.00734 |
| Haiku 4.5 | $0.00005 | $0.00367 |
Grade A, and why
superbuild 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- superbuild — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Superbuild: Plan Execution Engine
Execute implementation plans one phase at a time with strict quality enforcement, test verification, and conventional commit generation.
Overview
Superbuild is a rigid execution engine for implementation plans. It enforces:
- Phase-by-phase execution (no skipping ahead)
- Definition of Done verification before phase completion
- Test presence and passing verification
- Linter/formatter/typechecker enforcement
- Conventional commit message generation per phase
This is NOT a planning skill. Use superplan to create plans, then superbuild to execute them.
Critical Workflow
┌─────────────────────────────────────────────────────────────────────┐
│ SUPERBUILD EXECUTION FLOW │
│ (REPEAT FOR EACH PHASE) │
├─────────────────────────────────────────────────────────────────────┤
│ │
│ 1. INGEST PLAN │ User provides plan document path │
│ ↓ │ NO PLAN = EXIT (ask user, then exit if none) │
│ 2. READ PHASES │ Output ALL phases with estimates │
│ ↓ │ IF context high → suggest compact first │
│ 3. EXECUTE PHASE │ One phase at a time (or parallel if marked) │
│ ↓ │ USE SUB-AGENTS for parallel phases │
│ 4. ENFORCE DOD │ Tests exist? Tests pass? Linter? Formatter? │
│ ↓ │ ALL must pass → continue. ANY fail → STOP │
│ 5. UPDATE PLAN │ Check off tasks, update status in plan file │
│ ↓ │ ⚠️ THIS HAPPENS AFTER EVERY PHASE │
│ 6. COMMIT MSG │ Generate conventional commit (NEVER git ops) │
│ ↓ │ User handles all git operations │
│ 7. FUNCTIONAL TEST│ Explain how to test. Offer integration script │
│ ↓ │ NEVER auto-create scripts. ALWAYS ask first │
│ 8. STOP │ Full stop. Suggest compact. Wait for user. │
│ │ OVERRIDE: --build-all flag continues │
│ │
│ ════════════════════════════════════════════════════════════════ │
│ Steps 3-8 repeat for EACH PHASE. Plan updates after EVERY phase. │
│ ════════════════════════════════════════════════════════════════ │
│ │
└─────────────────────────────────────────────────────────────────────┘
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 486 lines · 51 tokens per session scan A 8a34ede6ac78
superbuild is a skill published in the GitHub repository asteroid-belt/skulto (50 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 3,672 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.