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/ooooooooooooooooooop/agent-tools/execution-disciplinenpx skills add ooooooooooooooooooop/agent-tools --skill execution-disciplinegit clone --depth 1 https://github.com/ooooooooooooooooooop/agent-toolsWhat 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 | $0.00199 | $0.09857 |
| Opus 5 | $0.00100 | $0.04928 |
| Sonnet 5 | $0.00040 | $0.01971 |
| Haiku 4.5 | $0.00020 | $0.00986 |
Grade A, and why
execution-discipline 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.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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_event180s 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）
- INVALID / FAIL / PARTIAL 意味着"继续修"，不是"可以交差了"。
- 收到门禁拒绝后先回答三个问题再决定下一步：根因在哪（数据/构造/门禁本身）？修哪里能过？需要什么证据证明修好了？
- 禁止向用户输出"是否继续？/你怎么看 A/B/C？/待决策"这类抛回；只有存在确实不可自行裁决的方向分歧时才问，且一次问完。
- 措辞从"待决策"改为"我将继续做 X，因为 Y"。
- 用户写死的门禁（如"B/C 失败则停止"）不允许在执行端悄悄重定义语义；确需调整，必须显式向用户说明理由并获批。
遇阻自救三连（检查设计 → 联网搜索 → 真正推进）
接上一条：遇到任何问题、失败、门禁拒绝或"似乎无法继续"时，不要记录阻塞或抛回用户，默认按以下顺序自动推进，不添加人工环节：
- 先检查设计：追调用链、查门槛/终态，用证据判定是"实现问题"还是"机制缺口"（grep 入口、读源码、跑最小复现）。
- 再联网搜索：内置
web_search不可用则走 CLI worker（queue_cli_request，显式target_model+effort，极窄探针，结构化回收），对照业界做法。 - 然后真正推进：把诊断变成系统层改动（代码/门禁/机制）+ 回归测试 + 验证生效，而不是写报告或加文档规则。
三连做完前禁止记 blocked/BLOCKED；只有无可用工具、无替代路径、无新增证据且达到预算才算确认阻塞。难度/不确定性不是阻塞理由。
三连是 Recovery Ladder 的快速版；完整恢复路径、失败分类与停止裁决见下方「Recovery Ladder 与合法停止策略」（canonical，其他 Skill 的停止/恢复规则不得比它更宽松）。
自主执行契约（Autonomy Execution Contract，canonical）
What ships with it
4 files 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.
- 2d ago First seen · 285 lines · 199 tokens per session scan A ef9aefd53d44
execution-discipline is a skill published in the GitHub repository ooooooooooooooooooop/agent-tools (2 stars, last pushed 3d ago), licensed MIT. It adds 199 tokens to every session and 9,857 once invoked, about $0.0010 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
zlog
Multi-agent session log compressor and storage optimizer. Compresses .log, .out, .txt, .trace (>10KB) to .zst, .xz, or .gz (saving 77%-99.9% disk space) across /.gemini, /.config/Cursor, /.ollama, /.claude, /.windsurf, /.codex, etc. Auto-discovers AI log dirs, purges empty 0-byte logs. Safe for concurrent…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
ai-security
../../../engineering-team/skills/ai-security/SKILL.md.
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
ctf-malware
Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…