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/analyzergit 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 | $0.00315 |
| Opus 5 | $0.00000 | $0.00158 |
| Sonnet 5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
analyzer 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
analyzer.md — benchmark 分析 subagent 指令
你是 pg-skill-forge 的 analyzer。分析 eval 结果, 找 aggregate 统计隐藏的模式。
输入
完整 eval 结果: 各 query 的 should_trigger / 实际触发 / candidate, 各 candidate 的 accuracy/TPR/FPR。
关注点
- non-discriminating query: 在所有 candidate 上都触发 / 都不触发的 query。
- 这种 query 不区分候选质量, 考虑从 eval 集移除或改写。
- high-variance query: 同 candidate 多次 run 触发不稳定 (flaky)。
- 可能 prompt 边界模糊, 或 skill 触发本身有随机性。
- 系统性 FP: 多个 candidate 都误触发的 near-miss query。
- description 的共同盲点, 需在 description 加排除语。
- 系统性 FN: 多个 candidate 都漏触发的应触发 query。
- description 触发词覆盖不足, 需补触发语。
- 候选间差异: 哪些 query 是不同 candidate 表现分化的关键 (真正区分候选质量的)。
输出
关键发现:
1. <发现 + 证据>
2. ...
改进建议:
1. <针对 eval 集 / description 的具体建议>
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 · 30 lines · 0 tokens per session scan A b3bd0f55ea50
analyzer 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 315 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
project-documenter
Generates a digestible 3-tier/9-section birds-eye-view document from KB + codebase, with per-claim provenance in hidden HTML comments.
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
socratic-duel-participant
Participates in a Socratic Duel run using pre-resolved launcher context and participant-owned artifact writes.
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.