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 agentmods add skills/sterlingchin/marvin-template/software-engineeringnpx skills add SterlingChin/marvin-template --skill software-engineeringgit clone --depth 1 https://github.com/SterlingChin/marvin-templateWrote 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/sterlingchin/marvin-template/software-engineering)<a href="https://agentmods.dev/skills/sterlingchin/marvin-template/software-engineering"><img src="https://agentmods.dev/badge/skills/sterlingchin/marvin-template/software-engineering.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01401 |
| Opus 5 | $0.00056 | $0.00700 |
| Sonnet 5 | $0.00022 | $0.00280 |
| Haiku 4.5 | $0.00011 | $0.00140 |
Grade A, and why
software-engineering 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Engineering with gstack
MARVIN uses gstack as its software engineering toolkit. gstack provides specialized development workflow skills. MARVIN provides project management, orchestration, and lifecycle tracking.
Boundary: This skill never re-describes gstack's methodology. It routes to the right gstack skill and handles MARVIN-specific bookkeeping. gstack's own SKILL.md files take over once invoked.
Step 1: Prerequisite Check
Verify gstack is installed:
[ -d ~/.claude/skills/gstack ] && echo "GSTACK_INSTALLED" || echo "GSTACK_MISSING"
If GSTACK_MISSING:
Tell the user: "Setting up your dev toolkit (one-time per machine)..."
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup
If the clone fails (network error, repo unavailable), tell the user: "gstack isn't available right now. I can still build software using general-purpose agents, but without the specialized review/QA/debug methodology. Want to proceed?"
If they say yes, proceed without gstack. Skip all gstack skill references below and use standard development practices.
Step 2: Route to gstack
Based on user intent, invoke the appropriate gstack skill:
| Intent signal | Action |
|---|---|
| "Build an app/tool/service that..." (new software concept) | Invoke /office-hours |
| "Review the plan", "validate before building" | Invoke /autoplan |
| "CEO review" / "eng review" / "design review" (specific) | Invoke /plan-ceo-review, /plan-eng-review, or /plan-design-review |
| "Build this feature", "implement this" (focused work) | Write code, then invoke /review |
| "Implement this PRD" (large, multi-requirement) | Go to Step 3: PRD Decomposition |
| "Review this code", "check my diff", "pre-merge review" | Invoke /review |
| "Fix this bug", "debug this", "why is this broken" | Invoke /investigate |
| "Test this", "QA this URL", "check this page" | Invoke /qa |
| "Ship it", "push and PR", "create a PR" | Invoke /ship |
| "Deploy this", "merge and deploy" | Invoke /land-and-deploy |
| "Check production", "monitor the deploy" | Invoke /canary |
| "Security audit", "check for vulnerabilities" | Invoke /cso |
| "Update the docs", "docs are stale" | Invoke /document-release |
| "What have we learned", "show learnings" | Invoke /learn |
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.
- 4d ago First seen · 158 lines · 111 tokens per session scan A 09a8274279df
software-engineering is a skill published in the GitHub repository SterlingChin/marvin-template (1,017 stars, last pushed 16d ago), licensed MIT. It adds 111 tokens to every session and 1,401 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…