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 auditor-succession-promptgit 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/auditor-succession-prompt)<a href="https://agentmods.dev/skills/blackzhanzhan/cyber-ming-protocol/auditor-succession-prompt"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/auditor-succession-prompt/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/auditor-succession-prompt"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/auditor-succession-prompt.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 | $0.00093 | $0.01506 |
| Opus 5 | $0.00046 | $0.00753 |
| Sonnet 5 | $0.00019 | $0.00301 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
auditor-succession-prompt 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 12d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditor Succession Prompt
Compatibility Note
- This is an IDE-side packaging skill.
- It prepares a copy-ready renewal packet for a fresh Web audit seat.
- It does not turn the IDE into the final auditor, and it does not replace Web-side audit templates.
- If the current project exposes a parent governance skill such as
skill/global_rules/SKILL.mdor~/.codex/skills/global_rules/SKILL.md, read and obey it first.
Use When
- The current auditor/review window has likely decayed, become narrative-contaminated, or is no longer clearly distinguishing current evidence from old arguments.
- The user explicitly wants to spin up a fresh auditor seat from the executor side.
- You need a ready-to-paste prompt package that defines the new auditor's identity, duties, evidence scope, and no-touch boundaries.
Default Boundary
- Under the Seven-Stars protocol, auditor renewal is normally the second beat, not the first.
- If the evidence suggests only the executor has decayed and the auditor is still clear, say so briefly and recommend renewing the executor first.
- If the user explicitly requests auditor renewal anyway, continue and package the renewal packet.
Responsibility
- Your job is to help the human mint a fresh auditor seat.
- Package only what the new auditor should inherit:
- law and role boundary
- current project report
- current evidence bundle
- current questions awaiting judgment
- Exclude stale argument chains, long emotional debates, and old verdicts presented as settled truth.
Read-Only Red Line
- Do not perform the audit locally as if you were the renewed auditor.
- Do not output code patches, implementation steps, or repository edits as a substitute for audit routing.
- Do not forward raw full-chat transcripts by default.
- Do not let the new auditor inherit the old auditor's conclusions without current evidence.
Required Input Gathering
Before composing the packet, extract only the minimum set that the new auditor actually needs:
- Current case title or task summary
- Why auditor renewal is being triggered
- Current project report or current-state snapshot
- Evidence bundle available now
- Concrete claims that need audit
- Known risks or unresolved disputes
- What the human wants the new auditor to judge now
What ships with it
1 file 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.
- 12d ago First seen · 114 lines · 93 tokens per session scan A 4b50a9aa1f99
auditor-succession-prompt is a skill published in the GitHub repository blackzhanzhan/Cyber-Ming-Protocol (56 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 1,506 once invoked, about $0.0005 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
pr-reviewing
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.
code-review
Use after completing implementation steps and before merging — reviews against plan and HOTL contracts.
requesting-code-review
Use at executor review checkpoints to dispatch the code-reviewer agent with structured context — git range, workflow contracts, and verification evidence.
receiving-code-review
Use when review findings arrive — verify each claim against the codebase and HOTL contracts before making changes. Governs how agents respond to review feedback.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.