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/quantsquirrel/claude-forge-smith/monitornpx skills add quantsquirrel/claude-forge-smith --skill monitorgit clone --depth 1 https://github.com/quantsquirrel/claude-forge-smithWrote 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/quantsquirrel/claude-forge-smith/monitor)<a href="https://agentmods.dev/skills/quantsquirrel/claude-forge-smith/monitor"><img src="https://agentmods.dev/badge/skills/quantsquirrel/claude-forge-smith/monitor.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 5.1 | $0.00046 | $0.01408 |
| Opus 5 | $0.00023 | $0.00704 |
| Sonnet 5 | $0.00009 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
monitor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Monitor
스킬 품질을 분석하고 업그레이드 우선순위를 추천합니다.
핵심 원칙: 사용량 ≠ 품질. 품질 점수로 추천하고, 사용량은 영향력 지표로만 참고.
Quick Reference
| Step | Action |
|---|---|
| 1 | 스킬 목록 스캔 (all scopes) |
| 2 | 각 스킬 유형 판별 (explicit/silent) |
| 3 | 유형별 품질 점수 계산 |
| 4 | 우선순위 기반 추천 생성 |
| 5 | 대시보드 출력 |
When to Use
- 어떤 스킬을 업그레이드해야 할지 모를 때
- 스킬 품질 현황을 파악하고 싶을 때
- 유형별(explicit/silent) 분석이 필요할 때
Arguments
| Argument | Description | Default |
|---|---|---|
--priority=HIGH|MED|LOW |
특정 우선순위만 표시 | all |
--type=explicit|silent|all |
특정 유형만 표시 | all |
--format=table|json |
출력 형식 | table |
Data Sources
source "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/local/forge}/hooks/lib/storage-local.sh"
# 스킬 유형 판별
get_skill_type "$skill_name"
# 품질 점수 계산 (유형별 기준 자동 적용)
get_skill_quality_score "$skill_name"
# 사용량 (참고용)
get_all_skills_summary
get_usage_trend "$skill_name"
Execution Steps
Step 1: Scan All Skills
스킬 위치 스캔:
~/.claude/skills/*/SKILL.md
~/.claude/plugins/**/skills/*/SKILL.md
.claude/skills/*/SKILL.md
Step 2: Analyze Each Skill
For each skill:
SKILL_TYPE=$(get_skill_type "$skill_name")
QUALITY_JSON=$(get_skill_quality_score "$skill_name")
USAGE_TREND=$(get_usage_trend "$skill_name")
Step 3: Calculate Priority
품질 기반 우선순위 (사용량과 무관):
| Priority | Condition | Meaning |
|---|---|---|
| HIGH | 품질 점수 < 40 | 구조적 문제, 즉시 개선 필요 |
| MED | 품질 점수 40-59 | 개선 여지 있음 |
| LOW | 품질 점수 60-79 | 선택적 개선 |
| READY | 품질 점수 ≥ 80 | 품질 양호 |
Impact 보정 (선택적):
- 사용량 ≥ 30 + 품질 낮음 → 영향력 높음 태그 추가
- 사용량 < 5 → 우선순위 영향 없음 (품질만 판단)
Step 4: Generate Output
Output Format
╔══════════════════════════════════════════════════════════════════════╗
║ 🔥 Forge Monitor ║
╠══════════════════════════════════════════════════════════════════════╣
║ Quality Analysis (품질 기반 - 사용량과 무관) ║
╠════════════════════════╤══════════╤═══════╤══════════╤═══════════════╣
║ Skill │ Type │ Score │ Grade │ Priority ║
╠════════════════════════╪══════════╪═══════╪══════════╪═══════════════╣
║ omc:git-master │ silent │ 45 │ C │ [HIGH] ⚡ ║
║ forge:forge │ explicit │ 72 │ B │ [LOW] ║
║ omc:analyze │ explicit │ 85 │ A │ [READY] ✓ ║
╚════════════════════════╧══════════╧═══════╧══════════╧═══════════════╝
╔══════════════════════════════════════════════════════════════════════╗
║ Upgrade Recommendations ║
╠══════════════════════════════════════════════════════════════════════╣
║ 1. [HIGH] omc:git-master (silent, score: 45) ║
║ → Missing: Red Flags section, trigger keywords insufficient ║
║ → Impact: 59 uses/month (high impact if fixed) ║
║ ║
║ 2. [MED] example-skill (explicit, score: 55) ║
║ → Missing: Quick Reference table ║
║ ║
║ 3. [LOW] forge:forge (explicit, score: 72) ║
║ → Suggestion: Add more examples ║
╚══════════════════════════════════════════════════════════════════════╝
Run `/forge:forge <skill-name>` to upgrade.
What ships with it
1 file 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.
- 5d ago First seen · 162 lines · 0 tokens per session scan A 8216a3c475ca
monitor is a skill published in the GitHub repository quantsquirrel/claude-forge-smith (2 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 1,408 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
a11y-analyzer
Accessibility analysis from session data — keyboard-only navigation patterns, focus order issues, screen reader compatibility, and accessibility regressions. Use when auditing a11y compliance, investigating accessibility bugs, or validating inclusive design.
changelog-detective
Detect what changed in the product by comparing before and after a deploy or date — find new behaviors, new errors, changed user flows, and unexpected side effects that weren't in the release notes. Use after a deploy or when the user suspects something changed but doesn't know what.
nps-proxy
Behavioral proxy for user satisfaction — use frustration signals, engagement patterns, and conversion behavior as a real-time NPS alternative. Use when the user wants to measure satisfaction but doesn't have survey data in Fullstory.
query-translator
Translate vague business questions into precise Fullstory queries — help users who know what they want to ask but not how to express it. Use when the user says "I want to know X but I'm not sure how to ask Fullstory.".
api-monitor
Monitor API call patterns from session data — endpoint latency, error rates, popular endpoints, and API-driven UX issues. Use when investigating backend performance impact on UX, API errors affecting users, or endpoint usage patterns.
benchmark-analyzer
Establish performance baselines and benchmarks — compare current metrics to historical averages, set targets, and track progress over time. Use when setting KPIs, establishing baselines, or measuring against goals.