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 echoVic/blade-code --skill provider-resilience-admission-and-observabilitygit clone --depth 1 https://github.com/echoVic/blade-codeWrote 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/echovic/blade-code/provider-resilience-admission-and-observability)<a href="https://agentmods.dev/skills/echovic/blade-code/provider-resilience-admission-and-observability"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/provider-resilience-admission-and-observability/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/echovic/blade-code/provider-resilience-admission-and-observability"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/provider-resilience-admission-and-observability.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00184 | $0.03906 |
| Opus 5 | $0.00092 | $0.01953 |
| Sonnet 5 | $0.00037 | $0.00781 |
| Haiku 4.5 | $0.00018 | $0.00391 |
Grade A, and why
knowledge-model-and-provider-runtime-provider-resilience-admission-and-observability 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 6d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Structure
该节点不是单一模块，而是包围每条物理 Provider stream 的横切控制面。它根据请求类别、 失败类型、候选位置、输出边界和显式容量配置选择不同恢复路径，并向所有运行表面投影 同一组临时事件。
Directory Layout
packages/cli/src/services/PiAIChatService.ts— 恢复、熔断、准入、deadline 与 fallback 总编排packages/cli/src/services/pi/providerRetry.ts— 错误分类、Retry-After 和退避packages/cli/src/services/pi/providerCircuitBreaker.ts— 进程共享 Closed/Open/HalfOpen 状态机packages/cli/src/services/pi/providerFailureDomain.ts— 敏感路由维度的规范化 HMAC 身份packages/cli/src/services/pi/providerRequestAdmission.ts— 进程共享加权公平队列与 permitpackages/cli/src/services/pi/providerRequestFootprint.ts— 等待请求 retained-footprint 估算packages/cli/src/services/pi/providerStall.ts— stall 生命周期契约packages/cli/src/services/pi/promptCacheBreakMonitor.ts— Session 级缓存断裂归因packages/cli/src/services/ProviderHealthService.ts— 受限、脱敏的真实 Provider 探测packages/cli/src/api/promptCacheMetrics.ts— 缓存指标归一化和展示格式
Decision Entry
PiAIChatService.streamChat()inpackages/cli/src/services/PiAIChatService.ts— 依据 recovery mode、request class、candidate index、circuit/admission 状态和首个真实 chunk 选择分支classifyProviderRetry()inpackages/cli/src/services/pi/providerRetry.ts— 将错误链和响应头归类为可重试或终止ProviderRequestAdmissionScheduler.admit()inpackages/cli/src/services/pi/providerRequestAdmission.ts— 决定立即运行、排队或按 count/bytes 拒绝
Branching Table
| 决策维度 | 分支 A | 分支 B |
|---|---|---|
| 准入是否启用 | 三个 concurrency 配置均未设置时不创建 scheduler，物理流直接访问 Provider | 任一 concurrency 配置显式设置或注入 scheduler 时，所有 primary/retry/fallback/probe 先取 permit |
| 请求类别 | root 用户阻塞请求为 foreground，可携带 bounded recovery |
Subagent/Hook 为 background，健康探测等为 internal，不继承扩展恢复 |
| Open circuit 与候选位置 | 非末 fallback 候选或 standard 请求立即拒绝该候选并继续 fallback/失败 | bounded foreground 的末候选在原 recovery deadline 内等待唯一 HalfOpen probe |
| 错误类型 | 408/409/429、5xx、transport、零输出 EOF 和 physical deadline 可进入有界重试 | quota/context、caller abort、recovery budget、idle timeout 不重试同一候选 |
| 流式提交边界 | 首个真实 chunk 前的可重试失败可重放并切换 fallback | text/reasoning/tool/usage/finish 任一已交付后 fail closed，不再重试或 fallback |
| 容量状态 | 队列为空且 capacity 可用时立即运行，超大请求不计 pending bytes | 必须等待时同时受 count、retained bytes 和 wait deadline 限制，0 表示 fail-fast |
| 时间预算 | admission 后启动每次 physical attempt 的 total deadline，语义事件只刷新 idle watchdog | foreground recovery 启动后覆盖 backoff、排队、建连和 stream，并在更早/相等时保持权威错误原因 |
| Prompt Cache | 关闭缓存时清除 Session 基线；普通启用使用 short retention | 带稳定 Session ID 的非官方 OpenAI-compatible completion endpoint 使用 long retention |
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.
- 6d ago First seen · 113 lines · 184 tokens per session scan A cd20bc775552
knowledge-model-and-provider-runtime-provider-resilience-admission-and-observability is a skill published in the GitHub repository echoVic/blade-code (178 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 3,906 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
histolab
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…