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 arkbriar/sisyphus-design --skill designgit clone --depth 1 https://github.com/arkbriar/sisyphus-designWrote 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/arkbriar/sisyphus-design/design)<a href="https://agentmods.dev/skills/arkbriar/sisyphus-design/design"><img src="https://agentmods.dev/badge/skills/arkbriar/sisyphus-design/design/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/arkbriar/sisyphus-design/design"><img src="https://agentmods.dev/badge/skills/arkbriar/sisyphus-design/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00020 | $0.01300 |
| Opus 5 | $0.00010 | $0.00650 |
| Sonnet 5 | $0.00004 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
Grade A, and why
sisyphus-design 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Skill
Design requirement: $ARGUMENTS
If no arguments provided, use AskUserQuestion to ask for the design requirement before proceeding.
Read before starting:
- template.md — document structure for drafting
- checklist.md — evaluation criteria for review
Phase 0: Research & Diverge (no human)
For trivial requirements (single flag, simple rename, obvious-one-solution), skip Phase 0 and Phase 1 — go directly to Phase 2. Present a single approach and identify the consumer as part of the decision presentation.
- Investigate: spawn a fresh research agent. It receives the design requirement and returns a structured summary: existing patterns found, constraints discovered, relevant prior art. Use web search whenever the domain is unfamiliar, prior art may exist, or something is unclear. Keep the main context clean — only bring back the summary.
- Think from first principles: what is this system fundamentally trying to do? What are the core constraints? Strip away conventional framing and reason from the ground up.
- Identify the critical path: the component or decision that, if wrong, makes the system fail regardless of how good everything else is.
- Generate 2-3 fundamentally different approaches that diverge on the critical path. Reuse obvious choices elsewhere.
- For each approach: one-sentence core idea, key trade-off, when it fails.
Phase 1: Interrogate (human)
Use AskUserQuestion to present concisely:
- Consumer: who implements from this design. Their first unanswered question.
- Critical path: the component or decision from Phase 0. Why this is the critical path.
- Approaches: the 2-3 from Phase 0 with trade-offs.
- Recommended approach: which one and why, based on the analysis.
- Discriminating questions: only questions whose answer would change the recommendation.
Wait for answers. User confirms, redirects, or asks follow-ups.
Phase 2: Decisions (human)
- Present the decisions as conversation text per the Decision Log format in template.md, including expanded blocks for critical path decisions and the end-to-end example trace (what data enters, what choices apply, what comes out — component-level state detail comes in Phase 3).
- Use AskUserQuestion to collect feedback — approve, reject, or comment. Keep the question short; do not repeat the decisions.
- Revise if rejected. All open questions must be answered before proceeding. If the user or the decisions reveal the requirement is more complex than initially assessed (especially if the trivial shortcut was used), return to Phase 0 for proper research.
What ships with it
2 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 · 89 lines · 20 tokens per session scan A 678f9dfead89
sisyphus-design is a skill published in the GitHub repository arkbriar/sisyphus-design (32 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,300 once invoked, about $0.0001 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
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…