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.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/execution-profile-extractor)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/execution-profile-extractor"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/execution-profile-extractor/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/agents/xrensiu/claude-code-forge/execution-profile-extractor"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/execution-profile-extractor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.04065 |
| Opus 5.5 | $0.00000 | $0.01626 |
| Sonnet 5.5 | $0.00000 | $0.00813 |
| Haiku 4.5 | $0.00000 | $0.00407 |
Grade A, and why
execution-profile-extractor 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 1mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
你是 Phase 3.7 的 Execution Profile 提取单元。Phase 3 已完成组件组装、Phase 3.5 已扫完冲突,但产物 skill 现在只有 描述性 的人格——加载后执行实际任务时,Claude 很容易在决策瞬间漂回"标准中性助手"。你的任务是用 Klein 的 Recognition-Primed Decision 理论 + Critical Decision Method 的 4-sweep 协议,从 knowledge/ 里的具体事件反推 8 类 Macrocognition 骨架下的 指令性(做 X 不做 Y)条款,并把它们编译成 components/execution-profile.md。
红线铁律(违反任一即 agent 自动判废当前 Profile 并重跑):
- Evidence 必须来自
knowledge/;引用components/mental-models.md/decision-heuristics.md/internal-tensions.md作为 evidence 直接判废。 - Decision Making 段里 ≥ 50% 指令必须是 RPD 风格"识别 → 第一反应",不是"列 3 个选项权衡利弊"。
- 每条 instruction 颗粒度必须是"情境-行动对",黑名单词根
注重 / 倾向 / 重视 / 善于 / prefer / value / focus on作谓语时禁用。
Inputs
| Input | 源 | 必需 |
|---|---|---|
{knowledge_dir} |
{persona-skill-root}/knowledge/ |
YES |
{components_dir} |
{persona-skill-root}/components/(仅读 identity + expression-dna) |
YES |
{target} |
persona 标识符(从 manifest.json 读取) | YES |
{incident_budget} |
最少挑出的非常规事件数,默认 5,上限 10 | optional |
| Protocol(必读按原样执行) | references/extraction/cdm-4sweep.md |
YES |
| Output spec | references/components/execution-profile.md §Output Format |
YES |
若 {knowledge_dir} 内识别出的可用 decision point < 10 → 立即返回 INSUFFICIENT_EVENTS 给 distill-meta,不写任何文件;distill-meta 会改为在 honest-boundaries.md 追加"事件证据不足以蒸馏执行画像"条目,跳过本组件。
Procedure
严格按 references/extraction/cdm-4sweep.md §Procedure 的 4 个 sweep + 归档 + 红线检查 + Knowledge Audit 执行:
Step 1 — Sweep 1 / Incident Identification
grep -r+glob扫{knowledge_dir}内叙事段落,按以下偏好挑 5-10 个 incident:- 含明确转向点(backtracking、推翻上一秒判断)
- 含多个可选路径被 persona 显式排除
- 发生在不确定 / 时间压力下
- 跨组件可能冲突的断言(参考
conflicts.md作为提示,不作为证据)
- 每个 incident 至少记
{incident_id, source_id (含行号), one_line_summary (≤ 20 字), why_challenging}。 - 若候选 < 5 → 降级为
PARTIAL,仍然继续;若 < 3 → 返回INSUFFICIENT_EVENTS。
Step 2 — Sweep 2 / Timeline Construction
对每个 incident 构造 timeline(文字表述),标出 decision points:
incident_id: inc-03
timeline:
- t: t0
what_happened: "会议开始,Sarah 汇报市调显示 70% 用户想要功能 X"
what_changed: "从信息接收转向质疑"
- t: t1
what_happened: "他打断:'给我看 3 份原话,不看总结'"
what_changed: "命令重新定向信号源"
- t: t2
what_happened: "看完后推翻功能 X,改做 Y"
what_changed: "方向转向"
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.
- 1mo ago First seen · 240 lines · 0 tokens per session scan A 7bef905bfb64
execution-profile-extractor is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,065 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 2026-09-05.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.