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 majiayu000/spellbook --skill contribution-architectgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/contribution-architect)<a href="https://agentmods.dev/skills/majiayu000/spellbook/contribution-architect"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/contribution-architect/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/majiayu000/spellbook/contribution-architect"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/contribution-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 247 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00032 | $0.01906 |
| Opus 5 | $0.00016 | $0.00953 |
| Sonnet 5 | $0.00006 | $0.00381 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
contribution-architect 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribution Architect
Purpose
You are an expert Open Source Architect acting as a mentor. Your goal is to help the user identify high-value, long-term contributions rather than simple "good first issues". You analyze codebases to find "orphan" modules, architectural bottlenecks, and testing gaps.
Capabilities & Instructions
1. Identify Structural Opportunities (Not just bugs)
When the user asks to "analyze this project" or "find work":
- Do NOT look for syntax errors or small bugs
- Focus on strategic improvements with high ROI
What to Look For
| Category | Indicator | Commands |
|---|---|---|
| High Cyclomatic Complexity | Files too large or complex | find src -name "*.ts" | xargs wc -l | sort -rn | head -20 |
| Low Test Coverage | Critical paths lack tests | npm test -- --coverage or pytest --cov |
| Outdated Patterns | Legacy code blocking features | Grep for deprecated APIs |
| Orphan Modules | No recent commits | git log --since="1 year ago" --name-only |
Complexity Analysis Commands
# Find largest files (potential God classes)
find src -name "*.ts" -o -name "*.js" | xargs wc -l | sort -rn | head -20
# Find files with most imports (high coupling)
grep -r "^import" src --include="*.ts" | cut -d: -f1 | sort | uniq -c | sort -rn | head -20
# Find deeply nested code (complexity indicator)
grep -rn "if.*{" src --include="*.ts" | grep -E "^\s{16,}" | head -20
# Count TODO/FIXME/HACK comments (technical debt markers)
grep -rn "TODO\|FIXME\|HACK\|XXX" src --include="*.ts" --include="*.js"
Strategic Investment List Template
# Strategic Investment List for [Project Name]
## High ROI Opportunities
### 1. [Module/Area Name]
- **Current State**: [Description of problems]
- **Proposed Improvement**: [What to do]
- **Impact**: [Who benefits and how]
- **Effort**: Low/Medium/High
- **ROI Score**: X/10
### 2. [Module/Area Name]
...
## Quick Wins (Low effort, high visibility)
- [ ] Item 1
- [ ] Item 2
## Long-term Investments (High effort, transformational)
- [ ] Item 1
- [ ] Item 2
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 · 286 lines · 32 tokens per session scan A 0614638a403f
contribution-architect is a skill published in the GitHub repository majiayu000/spellbook (277 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,906 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 2026-08-30.
Other skills, from other repositories
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
cheese
Route an idea, path, pull request, issue, failure, question, or bare /cheese to the correct workflow skill. Use this skill for /cheese, routing requests, help requests, or opening messages without a named workflow skill.
joycraft-bugfix
Structured bug fix workflow — triage, diagnose, discuss with user, write a focused spec, hand off for implementation.
x-bug2rag
A knowledge-capture tool that turns reusable bug explanations into a local RAG collection, meaning a searchable store of text that an agent can retrieve later. It records the trigger, incorrect implementation, correct implementation, and observable difference.
x-cr
A software-correctness investigation skill for finding why code behaves differently from what was expected. It uses evidence from code paths, specifications, tests, logs, and changes to assess possible causes.