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 suyoumo/ClawProBench --skill developer-setupgit clone --depth 1 https://github.com/suyoumo/ClawProBenchWrote 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/suyoumo/clawprobench/developer-setup)<a href="https://agentmods.dev/skills/suyoumo/clawprobench/developer-setup"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/developer-setup/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/suyoumo/clawprobench/developer-setup"><img src="https://agentmods.dev/badge/skills/suyoumo/clawprobench/developer-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.03746 |
| Opus 5.5 | $0.00020 | $0.01498 |
| Sonnet 5.5 | $0.00010 | $0.00749 |
| Haiku 4.5 | $0.00005 | $0.00375 |
Grade A, and why
developer-setup 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 1mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Workflow Setup
You are configuring the full developer workflow — commitment tracking, GitHub automation, tech debt tracking, security/QA reviews, product prioritization, and proactive briefings across multiple repositories.
Companion skills
These activate during conversation via keyword matching:
| Skill | When | What |
|---|---|---|
commitment-triage |
Obligations, deadlines | Signal extraction, commitment creation |
commitment-digest |
"show commitments" | Formatted status summary |
decision-capture |
Architecture/design decisions | Records decision + rationale |
delegation-tracker |
"waiting on @teammate" | Tracks delegation follow-ups |
idea-parking |
"park this idea" | Saves for later |
tech-debt-tracker |
"this is a hack", "refactor later" | Tracks tech debt, resurfaces weekly |
project-setup |
"add repo owner/repo" | Adds a new project with workflow |
security-review |
"security review", "check for vulnerabilities" | OWASP audit, auto-fix obvious issues |
qa-review |
"QA review", "test coverage", "edge cases" | Test plans, coverage gaps, regression risks |
review-readiness |
"ready to merge?", "PR readiness" | Tracks which reviews are complete per branch |
product-prioritization |
"what to build next", "prioritize" | Evidence-based feature scoring, demand analysis |
github |
GitHub API operations | REST API with credential injection |
github-workflow |
Workflow automation reference | Issue-to-merge pipeline templates |
review-checklist |
Pre-merge review | 55+ verification items |
If any are missing from skills/, tell the user which ones are needed.
Step 1: Setup questions (4, no timezone)
- Repos: Which GitHub repos do you work on? (1-5, format:
owner/repo) - Role: Solo maintainer, team member, or team lead? (Affects delegation vs personal tracking)
- Per-repo: For each repo — who are maintainers/reviewers? Do you use a staging branch?
- AI agents: Do any bots create PRs? (Dependabot, Copilot, internal agents) — these get tracked separately in digests with shorter stale thresholds
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.
- 1mo ago First seen · 235 lines · 49 tokens per session scan A 4015705737e5
developer-setup is a skill published in the GitHub repository suyoumo/ClawProBench (827 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,746 once invoked, about $0.0002 per session on Opus 5.5. 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
Evaluation
Frames model, prompt, and system evaluation as a reproducible experiment with baselines, datasets, and explicit metrics.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
unified-llm-api
Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
benchmark-design
Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline, or import a published Benchmark package.
remote-claude-code
Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via…