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/superduke/ganvil/evaluatenpx skills add superduke/ganvil --skill evaluategit clone --depth 1 https://github.com/superduke/ganvilWhat 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 | $0.00047 | $0.00609 |
| Opus 5 | $0.00023 | $0.00304 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
evaluate 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ganvil Evaluate — Standalone QA Evaluation
Evaluate an existing project or codebase using the ganvil evaluation framework, without requiring a prior plan or build.
What to Do
-
Determine the project type:
- If
$ARGUMENTSstarts with "frontend" or "backend", use that classification - Otherwise, examine the project structure to auto-detect:
- Has
package.jsonwith frontend frameworks (React, Vue, Svelte, etc.) → FRONTEND - Has backend files (Python, Go, Rust, Java server code,
requirements.txt,Cargo.toml, etc.) → BACKEND - Has both → evaluate as FULLSTACK (backend first, then frontend)
- Has
- If
-
Create
ganvil-artifacts/directory if it doesn't exist. -
For frontend evaluation: Delegate to the frontend-evaluator agent.
- The evaluator will start the application, interact via browser, and score on:
- Design Quality (≥7 to pass)
- Originality (≥7 to pass)
- Craft (≥6 to pass)
- Functionality (≥7 to pass)
- Output:
ganvil-artifacts/frontend-evaluation.md
- The evaluator will start the application, interact via browser, and score on:
-
For backend evaluation: Delegate to the backend-evaluator agent.
- The evaluator will start the server, run tests, hit API endpoints, and score on:
- API Correctness (≥7 to pass)
- Data Integrity (≥7 to pass)
- Code Quality (≥6 to pass)
- Functional Completeness (≥7 to pass)
- Output:
ganvil-artifacts/backend-evaluation.md
- The evaluator will start the server, run tests, hit API endpoints, and score on:
-
For fullstack evaluation: Run both evaluators, backend first.
-
Summarize the evaluation results, highlighting:
- Overall pass/fail per dimension
- Critical bugs found
- Top recommendations for improvement
Usage
# Auto-detect project type and evaluate
/ganvil:evaluate
# Evaluate only the frontend
/ganvil:evaluate frontend
# Evaluate with focus
/ganvil:evaluate frontend focus on mobile responsiveness and accessibility
# Evaluate backend
/ganvil:evaluate backend focus on API error handling
Note
This skill evaluates code as-is. It does not require a ganvil-artifacts/spec.md or sprint contracts — the evaluator will assess the project against general quality standards. However, if a spec exists from a prior /ganvil:plan, the evaluator will use it for more targeted evaluation.
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.
- 2d ago First seen · 68 lines · 47 tokens per session scan A 2bb61e286edf
evaluate is a skill published in the GitHub repository superduke/ganvil (3 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 609 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
understand-codebase
Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…
lauren
Use this skill when the user wants to plan a piece of implementation work and add it to the lauren queue (the lauren todo / backlog). Typical phrasings include "add this to lauren", "add this to the lauren todo", "lauren this", "let's make a lauren plan for X", or "plan this with lauren". The plan is then executed…
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.