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 skills add blackzhanzhan/Cyber-Ming-Protocol --skill approved-checklist-executorgit clone --depth 1 https://github.com/blackzhanzhan/Cyber-Ming-ProtocolWrote 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/skills/blackzhanzhan/cyber-ming-protocol/approved-checklist-executor)<a href="https://agentmods.dev/skills/blackzhanzhan/cyber-ming-protocol/approved-checklist-executor"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/approved-checklist-executor/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/skills/blackzhanzhan/cyber-ming-protocol/approved-checklist-executor"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/approved-checklist-executor.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 | $0.00058 | $0.02378 |
| Opus 5 | $0.00029 | $0.01189 |
| Sonnet 5 | $0.00012 | $0.00476 |
| Haiku 4.5 | $0.00006 | $0.00238 |
Grade A, and why
approved-checklist-executor 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 9d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approved Checklist Executor
Prerequisite: read and obey the repository parent policy at skill/global_rules/SKILL.md first.
Use When
- A checklist or one or more atomic slices have already been approved.
- The task is now in execution state.
- The run mode may be:
- single-slice mode
- pulse mode
Core Rule
- Default to pulse progression when the approved checklist is fully authorized and no blocker appears.
- Preserve atomic discipline at all times:
- one slice
- one verification
- one commit
- one
git status --short
- Execution should stay attached to the current campaign tree.
- A child fix may pause the parent campaign, but it may not silently become the new root campaign.
- Default to continuous execution inside the approved campaign.
- Do not stop merely because new information appears. Stop only when that information crosses a declared red line, invalidates the slice's core assumption, or creates scope drift that would make further execution dishonest.
- If the project exposes an execution lock such as
active_contract.json, treat it as the current execution truth and continue from it rather than narrating a fresh broad contract. - If the project also exposes a contract runner such as
openclaw_harness_contract_runner.py, use it as the default execution-state transition entrypoint.
Explicit Submode: One-Breath Mode / 一口气模式
This submode is not the default.
It activates only when the user explicitly says things like:
one-breath modepush continuouslydo not stop; finish the approved checklistcontinue until blocked一口气模式开启一口气模式用一口气模式推进不要停,一口气做完
When active, add these stronger rules on top of the normal executor discipline:
- keep moving continuously until a real blocker, failed verification, missing secret, or crossed red line appears
- emit a concrete progress update at least every
3 minutesduring long-running work - stop only on a real blocker, failed verification, missing secret, or crossed red line
- if a red line is crossed, write the smallest possible delta sub-contract and continue from it
- after the delta sub-contract is resolved, automatically return to the main approved contract
- do not inflate the pause into a fresh broad plan unless continuing would be dishonest
- do not pause externally just because one commit or one slice has completed; archive it and keep moving
- write detailed slice-level bookkeeping into harness artifacts rather than turning every slice boundary into a conversational stop
- use progress reports only in this structure, translated to the user's working language:
Proven/已证明Not Proven/未证明Why It Did Not Complete/为什么没做成
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.
- 9d ago First seen · 193 lines · 58 tokens per session scan A 075296044691
approved-checklist-executor is a skill published in the GitHub repository blackzhanzhan/Cyber-Ming-Protocol (56 stars, last pushed 4mo ago), licensed MIT. It adds 58 tokens to every session and 2,378 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
workspace
Dynamic multi-repo and monorepo awareness for Claude Code. Analyze workspace topology, track API contracts, and maintain cross-repo context.
ticket-craft
Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing.
team-coordination
Multi-person projects - shared state, todo claiming, handoffs.