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 knowledgesgit 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/knowledges)<a href="https://agentmods.dev/skills/echovic/blade-code/knowledges"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/knowledges/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/knowledges"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/knowledges.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 | $0.00104 | $0.04314 |
| Opus 5.5 | $0.00042 | $0.01726 |
| Sonnet 5.5 | $0.00021 | $0.00863 |
| Haiku 4.5 | $0.00010 | $0.00431 |
Grade A, and why
knowledge-blade-code 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Structure
Blade Code 是 TypeScript monorepo：packages/cli 同时承载无状态 Agent 核心、Session runtime、工具平台、Provider 与 CLI/Server/ACP 表面；packages/cli/web 是 React Web 投影；packages/vscode 提供编辑器桥接。权威会话状态来自持久事件与资源快照，而不是任一 UI Store。
Directory Layout
packages/cli/src/agent/— Agent 决策循环、Session runtime、子代理与团队编排packages/cli/src/context/— transcript、事件日志、上下文压缩与恢复packages/cli/src/tools/— 工具契约、注册表、执行管线与内置工具packages/cli/src/services/— Provider、Session 与共享服务实现packages/cli/src/mcp/、packages/cli/src/plugins/、packages/cli/src/skills/、packages/cli/src/hooks/、packages/cli/src/lsp/— 扩展生态packages/cli/src/ui/、packages/cli/src/server/、packages/cli/src/acp/— TUI、Web 服务与 ACP 宿主表面packages/cli/web/— React + Vite Web 客户端packages/vscode/— VS Code WebSocket 桥接扩展packages/cli/tests/、packages/cli/scripts/、.github/workflows/— 测试、资格认证和发布链路
Key Entry Points
packages/cli/src/blade.tsx— CLI/TUI、Headless、ACP、Web/Serve 的统一进程入口packages/cli/src/agent/Agent.ts— 无状态决策器和连续 Goal 推进入口packages/cli/src/agent/runtime/SessionRuntime.ts— Session 资源与生命周期聚合边界packages/cli/src/context/events/SessionEventLog.ts— committed event 的持久化与跨表面扇出入口packages/cli/src/server/server.ts— Hono 服务、调度器和关闭流程装配入口packages/cli/web/src/main.tsx— Web 客户端入口
Gotchas
- 不要把 TUI/Web Zustand Store 当作权威状态；恢复、重连和跨表面一致性必须从 committed Session 事件或持久 metadata 投影 (
packages/cli/src/context/events/SessionEventLog.ts,packages/cli/src/store/,packages/cli/web/src/store/) Agent的无状态不等于 Session 无状态；模型选择、工具目录、MCP/LSP/Browser、durable inbox 和执行租约都由SessionRuntime持有，绕开它会破坏恢复与清理 (packages/cli/src/agent/Agent.ts,packages/cli/src/agent/runtime/SessionRuntime.ts)ToolKind.ReadOnly是权限分类而非幂等或并发证明；并发、流式预启动和瞬态重放分别由独立 capability 控制 (packages/cli/src/tools/types/ToolTypes.ts,packages/cli/src/tools/core/createTool.ts)- Web、ACP 与 Headless 不是三套 Agent runtime；表面层应适配同一
SessionRuntime/loop event 契约，不能在客户端重建业务状态机 (packages/cli/src/server/routes/session.ts,packages/cli/src/acp/Session.ts,packages/cli/src/commands/headless.ts) - docs 根目录中文与
docs/en英文是同一用户契约，而 changelog 页面由工作流生成；不要直接编辑生成的 docs changelog (AGENTS.md,.github/workflows/docs.yml)
What ships with it
48 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.
- agent-execution-and-orchestration/agent-teams/SKILL.md 7.8 KB
- agent-execution-and-orchestration/decision-loop-and-completion/SKILL.md 10 KB
- agent-execution-and-orchestration/goals-tasks-and-scheduling/SKILL.md 11 KB
- agent-execution-and-orchestration/SKILL.md 7.0 KB
- agent-execution-and-orchestration/subagent-runtime/SKILL.md 9.2 KB
- engineering-quality-and-delivery/build-release-and-documentation/SKILL.md 10 KB
- engineering-quality-and-delivery/performance-security-and-snapshot-gates/SKILL.md 9.9 KB
- engineering-quality-and-delivery/real-api-qualification-and-e2e/SKILL.md 10 KB
- engineering-quality-and-delivery/SKILL.md 8.5 KB
- engineering-quality-and-delivery/unit-integration-and-shared-test-harnesses/SKILL.md 9.0 KB
- extension-ecosystem/hooks-and-behavior-interception/SKILL.md 11 KB
- extension-ecosystem/lsp-code-intelligence/SKILL.md 10 KB
- extension-ecosystem/mcp-protocol-runtime/SKILL.md 12 KB
- extension-ecosystem/plugin-lifecycle-and-marketplace/SKILL.md 12 KB
- extension-ecosystem/SKILL.md 7.4 KB
- extension-ecosystem/skills-and-custom-commands/SKILL.md 11 KB
- interaction-surfaces/acp-host-integration/SKILL.md 8.9 KB
- interaction-surfaces/cli-bootstrap-headless-and-print/SKILL.md 7.7 KB
- interaction-surfaces/hono-server-api-and-streaming/SKILL.md 8.8 KB
- interaction-surfaces/SKILL.md 8.0 KB
- interaction-surfaces/terminal-ui/SKILL.md 8.5 KB
- interaction-surfaces/vscode-bridge/SKILL.md 5.6 KB
- interaction-surfaces/web-client/SKILL.md 10 KB
- model-and-provider-runtime/model-catalog-configuration-and-credentials/SKILL.md 7.6 KB
- model-and-provider-runtime/provider-resilience-admission-and-observability/SKILL.md 15 KB
- model-and-provider-runtime/provider-transport-and-context-adaptation/SKILL.md 7.9 KB
- model-and-provider-runtime/SKILL.md 6.3 KB
- session-state-and-context/active-turn-interactions-and-recovery/SKILL.md 11 KB
- session-state-and-context/context-compaction-token-budget-and-memory/compaction-pipeline-and-checkpoints/SKILL.md 9.4 KB
- session-state-and-context/context-compaction-token-budget-and-memory/project-auto-memory/SKILL.md 7.1 KB
- session-state-and-context/context-compaction-token-budget-and-memory/SKILL.md 7.5 KB
- session-state-and-context/durable-transcript-and-event-projection/SKILL.md 11 KB
- session-state-and-context/session-catalog-fork-rewind-and-export/SKILL.md 9.8 KB
- session-state-and-context/SKILL.md 6.7 KB
- tool-and-automation-platform/browser-automation/SKILL.md 10 KB
- tool-and-automation-platform/filesystem-search-and-atomic-patching/SKILL.md 9.3 KB
- tool-and-automation-platform/integration-and-workflow-tool-adapters/SKILL.md 11 KB
- tool-and-automation-platform/shell-process-and-worktree/SKILL.md 9.2 KB
- tool-and-automation-platform/SKILL.md 7.5 KB
- tool-and-automation-platform/tool-contracts-and-registry/SKILL.md 10 KB
- tool-and-automation-platform/tool-execution-pipeline/SKILL.md 12 KB
- workspace-policy-and-shared-foundations/capacity-lifecycle-and-egress/SKILL.md 12 KB
- workspace-policy-and-shared-foundations/layered-configuration-and-runtime-settings/SKILL.md 9.7 KB
- workspace-policy-and-shared-foundations/permissions-and-workspace-trust/SKILL.md 9.9 KB
- workspace-policy-and-shared-foundations/runtime-state-bootstrap-and-observability/SKILL.md 14 KB
- workspace-policy-and-shared-foundations/shared-api-and-runtime-schemas/SKILL.md 8.5 KB
- workspace-policy-and-shared-foundations/SKILL.md 9.7 KB
- workspace-policy-and-shared-foundations/workspace-resource-snapshots-and-project-instructions/SKILL.md 10 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.
- 1mo ago First seen · 136 lines · 104 tokens per session scan A ddc709412126
knowledge-blade-code is a skill published in the GitHub repository echoVic/blade-code (181 stars, last pushed 3d ago), licensed MIT. It adds 104 tokens to every session and 4,314 once invoked, about $0.0004 per session on Opus 5.5. 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
clinical-reports
Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…
clinical-decision-support
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.
immunology-assays
Computational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use…
molecular-cloning
Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.
geo-database
Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.