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 liyingsong99/AIBridge --skill aibridge-development-workflowgit clone --depth 1 https://github.com/liyingsong99/AIBridgeWrote 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/liyingsong99/aibridge/aibridge-development-workflow)<a href="https://agentmods.dev/skills/liyingsong99/aibridge/aibridge-development-workflow"><img src="https://agentmods.dev/badge/skills/liyingsong99/aibridge/aibridge-development-workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.00618 |
| Opus 5 | $0.00043 | $0.00309 |
| Sonnet 5 | $0.00017 | $0.00124 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
aibridge-development-workflow 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 8d 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.
What it actually says
AIBridge Development Workflow
入口边界
如误入本 Skill（纯问答/解释/只读分析），直接回答，停止展开分支和 Harness 探测
必读顺序
- 若存在
references/project-workflow-preferences.md，先读取它 - 读取
references/branch-selection.md，选择启用的主分支 - 只读取当前分支的
references/branches/<branch>.md - 进入开发、调试、审查、验证或 workflow 任务前读取
references/harness-readiness.md；只有运行时探测、resume、外部 executor、或业务命令失败需要 fallback 时，才继续读references/harness-readiness-detail.md - 仅在当前动作需要时读取：
risk-gates.md、coding-rules.md、checklist.md、debug-investigation-workflow.md、debug-investigation-checklist.md、editor-generation.md、profiler-debugging.md
路由不变量
- Skill 路由是 Preflight，不是业务模式
- 主分支只能从 preferences 启用的分支中自动选择；用户要求禁用分支时先确认
- 需求不清晰时先进入需求讨论分支；方案写入规则见
branches/requirements.md aibridge-development-workflow常驻；其它 Skill 仅在当前分支/phase 内有效，Mode Exit 后只保留 artifact refs 与 gate- Workflow report/manifest 默认作路径交接，不为常规状态读全文
工具不变量
- 项目侧能力以 Root Rule 与 preferences 为准；勿用
$CLI harness status做 enablement/freshness 预检 compile dotnet不能替代$CLI compile unity- 仅当 Root Rule / preferences 声明 Code Index 已启用且需定位 C# 声明时，才加载
aibridge-code-index agent/manualstep 需外部执行器或人工，并用workflow import回传；AIBridge CLI 不会自动执行
输出策略
输出格式与 Skill 列出策略见 branch-selection.md。最终回复不列 使用 Skills、已释放 Skills 或下一步建议 Skills；结构化续跑信息只放入 SkillHandoff
What ships with it
18 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.
- agents/openai.yaml 399 B
- references/branch-selection.md 4.7 KB
- references/branches/debug.md 1.4 KB
- references/branches/implementation.md 1.1 KB
- references/branches/orchestration.md 994 B
- references/branches/requirements.md 1.9 KB
- references/branches/review.md 818 B
- references/branches/validation.md 825 B
- references/checklist.md 2.5 KB
- references/coding-rules.md 1001 B
- references/debug-investigation-checklist.md 1.8 KB
- references/debug-investigation-workflow.md 2.1 KB
- references/editor-generation.md 6.8 KB
- references/harness-readiness-detail.md 2.6 KB
- references/harness-readiness.md 1.6 KB
- references/profiler-debugging.md 1.7 KB
- references/profiler-debugging.md.meta 155 B
- references/risk-gates.md 2.0 KB
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.
- 8d ago First seen · 38 lines · 86 tokens per session scan A 0016604992af
aibridge-development-workflow is a skill published in the GitHub repository liyingsong99/AIBridge (218 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 618 once invoked, about $0.0004 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
unity-debug
A workflow for investigating runtime errors in the Unity game-development editor, including null references and console messages.
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.
uloop-get-project-info
Get Unity project information via uloop CLI. Use when you need to check project settings, Unity version, platform, or other project metadata.