execution-discipline SKILL.md skillA
execution-discipline from ooooooooooooooooooop/agent-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ooooooooooooooooooop/agent-tools/execution-discipline@v0.3.0Pins v0.3.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ooooooooooooooooooop/agent-tools
- Path
skills/execution-discipline/SKILL.md- Versions recorded
- 5
- Latest version
- v0.3.0, committed Aug 28, 2026
- First version recorded
- Aug 25, 2026
- Size
- 34,751 bytes
- Repository stars
- 4
- License
- MIT
在 DSH 长程/多工具会话中强制九条执行纪律，防止高频反模式重演：禁止无 wait 轮询、禁止把门禁拒绝当交付物抛回决策、外部研究先探测通道再极窄探针、探查派子代理不肉身 Read、子代理派发带进度回报协议、回合结束零悬挂收尾、上下文预算（回合合并+结果落盘）。用于接手长任务、等待子代理/后台任务、发起外部研究、收到 INVALID/FAIL/PARTIAL 门禁结果、收到"重复工具调用"系统警告、需要读取多个源码文件或大文件，以及任何需要"执行层不空转、不惊群、不绕门禁"的执行场景。不用于单轮小修改或无需持久化的临时问答。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 执行纪律（Execution Discipline） > 本 skill 由一次真实长程会话审计（session-`<id>`）提炼而成。那次会话 13 小时、72 轮、12 次压缩、30 次无 wait 轮询、外部研究惊群空转约 90 分钟、多次把决策抛回用户，最终在 goal 8/8 耗尽时仍未完成。**这些错误全部有现成规则可依，缺的是执行时把它们当硬门禁。** 本 skill 把十条铁律固化为"执行点自查"，任何新会话在匹配场景下加载后必须逐条对照。 ## 十条铁律 ### 铁律一：等通知，不轮询（零轮询） - 子代理 / 后台任务 / CLI 请求完成时，系统会**主动推送完成通知**，无需查询。 - 派发后本轮立即收尾结束，等通知进入下一轮。 - 确需确认请求存在时，`list_agents` / `job_list` / `request_status` / `get_cli_requests` **只允许调用一次**；确认后转入单次长轮询：`job_output(job_id, wait=true, timeout_ms=60000)`、`request_result(request_id, wait_seconds=60~120)`、`wait_task_receipt(receipt_path, wait_seconds=60~120)`、`wait_supervisor_event(...)`。 - **长轮询超时返回 ≠ 有事件**：`wait_supervisor_event` 180s 超时后直接再次 wait（`since_seq` 推进），**禁止**在两次 wait 之间夹 `get_managed_claude_supervisor` / `list_managed_claude_supervisors` 查询——WAIT→GET 夹用就是轮询变体（2026-08-24 曾连续 44 分钟）。 - **收到"重复相同工具调用"系统警告 = 必须立即改变策略**：先读上次结果，换参数/换工具/换方案，绝不在同一调用上再试。 - **等待期必须并行推进，禁止纯等（2026-08-26 沉淀）**：长轮询/等 CLI 结果期间，先列出"不依赖该结果的待办"并逐个执行（读产物、查未闭合项、推进其他 todo），再回到轮询；**同一回合内连续 ≥2 次 request_result/job_output 之间没有其他工具调用 = 空转信号**。来源实证：2026-08-26 论文会话 Turn 7 的 16 次调用中 9 次输出 <200 tokens 的纯轮询，38 分钟内 Top1000 归属等可并行项未推进。 ### 铁律二：门禁结果是诊断信号，不是交付物（自主闭环） …
Read the whole file at its exact version.
How to install
mdr add ooooooooooooooooooop/agent-tools/execution-discipline@sha256:ef9aefd53d4482aeThe line at the top of this page pins the label v0.3.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_d6lrhf36bo2qoeba)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 25, 2026 and Aug 28, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.3.0 latest | 2026-08-28 | 278776e | 34,751 B | A | view · diff |
| v0.2.1 | 2026-08-26 | 7877509 | 28,742 B | A | view · diff |
| v0.2.0 | 2026-08-25 | 65a6278 | 27,941 B | A | view · diff |
| v0.2.0 | 2026-08-25 | b0709c1 | 26,914 B | A | view · diff |
| v0.2.0 | 2026-08-25 | 2525f8e | 25,278 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (34751 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ooooooooooooooooooop/agent-tools · 4 stars · license MIT · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_d6lrhf36bo2qoeba GET https://markdownregistry.com/api/v1/resolve?ref=ooooooooooooooooooop/agent-tools/execution-discipline GET https://markdownregistry.com/api/v1/blob/ef9aefd53d4482ae2ef7997a428ccac0aecc2d5c9725a3a519f8cbd3d4599205
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from ooooooooooooooooooop/agent-tools
Every file in ooooooooooooooooooop/agent-tools