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 free-development-modegit 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/free-development-mode)<a href="https://agentmods.dev/skills/blackzhanzhan/cyber-ming-protocol/free-development-mode"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/free-development-mode/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/free-development-mode"><img src="https://agentmods.dev/badge/skills/blackzhanzhan/cyber-ming-protocol/free-development-mode.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 | $0.00053 | $0.02045 |
| Opus 5 | $0.00026 | $0.01022 |
| Sonnet 5 | $0.00011 | $0.00409 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade A, and why
free-development-mode 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Free Development Mode
Role
This skill is the dedicated execution route for free development mode / 自由开发模式.
It is not the default implementation workflow.
It only activates after an explicit user opt-in such as:
enter free development modeuse free development modeswitch to free development mode开启自由开发模式进入自由开发自由长时开发模式
Core Rule
Once activated, execute directly under red-line control.
Do not fall back into repetitive approval-first ceremony unless:
- a hard red line is crossed
- scope changes materially
- the current route becomes dishonest
Long-running execution is allowed in this mode only when:
- the mainline remains explicit
- no hard red line is crossed
- the executor does not quietly mutate the requirement
- engineering discipline stays intact
- architecture discipline stays intact: ordinary implementation cannot smuggle architecture changes.
- data-model discipline stays intact: ordinary implementation cannot smuggle ER, migration, backfill, or persistence semantics changes.
Free-development mode now absorbs:
- Anthropic-style long-running harness scaffolding
- GSD-style context engineering and quality gates
But it does not become:
- a scripted frontdesk testing mode
- a process-theater planning mode
- a replacement for real frontdesk evidence
What To State Before Long Execution
Before a long autonomous push, state only these things:
- the mainline you are choosing
- the likely branch paths you may need
- the routes you must avoid
- the fake methods / poison methods you will not use
- the architecture nodes and data entities you expect to touch, and whether any amendment contract may be required
Do not re-outline the whole project unless a red line forces replanning.
Route Choice Discipline
When a problem is complex, choose one primary route and keep moving until evidence disproves it.
Preferred route order:
- same-case / replay-first
- architecture census or amendment contract when the real uncertainty is architectural
- ER/data-model census or amendment contract when the real uncertainty is durable data semantics
- probe-first when the real uncertainty is operational rather than architectural or data-model-shaped
- end-to-end truth path
- smallest live blocker first
- rollback or cleanup before expansion
- bounded concurrency only after parity is green
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 · 244 lines · 53 tokens per session scan A f7a4e346e3ec
free-development-mode is a skill published in the GitHub repository blackzhanzhan/Cyber-Ming-Protocol (56 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 2,045 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
loop-execution
Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.
executing-plans
Use when executing an implementation plan linearly with explicit human checkpoints between batches of tasks.
brainstorming
Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.
pr-reviewing
Review a PR across multiple dimensions — description, code changes, code scan, unit tests — using parallel subagents. Supports GitHub, GitLab, and enterprise platforms.
writing-plans
Use after design approval to create a dated executable workflow file with bite-sized tasks, exact file paths, and loop/gate definitions.
document-review
Optional utility for reviewing existing docs, external specs, hand-authored notes, or non-HOTL documents. HOTL design docs and workflows get structural lint + AI review; other documents get AI-only review with a generic rubric.