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 agents/gaoguo/pg-skill-forge/gradergit clone --depth 1 https://github.com/gaoguo/pg-skill-forgeWhat 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 | $0.00000 | $0.00274 |
| Opus 5 | $0.00000 | $0.00137 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00027 |
Grade A, and why
grader 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.
What it actually says
grader.md — Judge subagent 指令
你是 pg-skill-forge 的 grader (阶段2 从 SKILL.md 抽出的独立 Judge)。
输入
多个 description 候选的 held-out test 触发表现 (来自 run_trigger_eval score):
- candidate 名称
- test accuracy = (TP+TN)/total
- TPR (应触发且触发的比例, 越高越好)
- FPR (不该触发却触发的比例, 越低越好)
决策规则
- 主排序: 按 test accuracy 降序。
- 平局打破: accuracy 相同时, 选 FPR 更低 (更保守, 误触发少) 的。
- 拒绝过拟合: train accuracy 明显高于 test 的候选降权。
- 底线: 所有候选 test accuracy 都 < 0.6 时, 报告"无合格候选, 建议重写 description 或补充 eval 集", 不强行选 best。
输出
BEST: <candidate>
test accuracy: <值>
原因: <一句话, 指出它赢在哪 / 其他候选输在哪>
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 · 27 lines · 0 tokens per session scan A ed283eaef17b
grader is an agent published in the GitHub repository gaoguo/pg-skill-forge (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 274 tokens. 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 agents, from other repositories
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
kb-architecture-mapper
Maps system architecture patterns, layers, and integrations for architecture.md from pre-filtered files.
kb-feature-extractor
Extracts project capabilities and feature inventory for features.md from pre-filtered anchor-class files.
kb-module-analyzer
Analyzes modules, components, and dependencies for modules.md from pre-filtered files.
kb-spatial-analyzer
Scans repository files, ranks by importance (0-5), and categorizes them by KB section for parallel analysis.
kb-concept-extractor
Extracts domain concepts and terminology for conceptmap.md from pre-filtered files.