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 performance-security-and-snapshot-gatesgit 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/performance-security-and-snapshot-gates)<a href="https://agentmods.dev/skills/echovic/blade-code/performance-security-and-snapshot-gates"><img src="https://agentmods.dev/badge/skills/echovic/blade-code/performance-security-and-snapshot-gates.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 | $0.00172 | $0.02534 |
| Opus 5 | $0.00086 | $0.01267 |
| Sonnet 5 | $0.00034 | $0.00507 |
| Haiku 4.5 | $0.00017 | $0.00253 |
Grade A, and why
knowledge-engineering-quality-and-delivery-performance-security-and-snapshot-gates 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 4d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Structure
该节点聚合四种不同可信度的质量信号：直接压产品实现的资源不变量、依赖构建产物的性能预算、源码边界审计，以及只锁定展示字符串的快照。
Directory Layout
packages/cli/tests/performance/— CLI 启动、数据结构、Token 算法和可选真实仓库 benchmarkpackages/cli/web/tests/performance/— production Web bundle 的 gzip 预算packages/cli/tests/security/— 输入模式、路径、敏感文件与 Browser Tool 源码边界检查packages/cli/tests/snapshots/— 工具输出示例及 Vitest snapshotpackages/cli/scripts/run-security-tests.sh— 依赖审计、许可证和 outdated 辅助脚本scripts/bench-sqlite.mts— JSONL 与 SQLite 投影的独立人工 benchmarkpackages/cli/vitest.config.ts— performance/snapshot/security project 与 coverage 阈值.github/workflows/ci.yml— security、coverage、Chromium sandbox 和制品上传作业
Key Entry Points
performance、snapshot、securityprojects inpackages/cli/vitest.config.ts— 三类专用测试选择器packages/cli/tests/performance/regression/startup-time.test.ts— 对已构建 CLI 的启动相对回归packages/cli/web/tests/performance/bundle-size.test.ts— Web 入口、首屏与总 JS gzip 上限packages/cli/tests/security/browser-tool-boundary.test.ts— Browser Tool 禁止能力与 sandbox 源码契约packages/cli/tests/snapshots/outputs/tool-output.snap.test.ts— 快照生成入口
Branching Table
| 维度 | 分支 A | 分支 B |
|---|---|---|
| 性能对象 | BoundedOutputBuffer、KeyedMutexRegistry 直接压生产类并断言资源上限 |
token-counter benchmark 使用测试内算法，只比较相对速度 |
| 制品依赖 | startup 与 Web bundle 测试要求已有 dist |
纯数据结构 benchmark 可直接从源码运行 |
| benchmark 启用 | 默认 performance project 跳过真实仓库 benchmark | BLADE_RUN_REAL_REPO_BENCHMARK=1 才运行真实 Agent 仓库任务 |
| 安全证据 | Browser 边界测试读取生产源码并锁定禁用能力/sandbox 约束 | injection/path/sensitive-file 测试主要验证测试文件内定义的检测器 |
| 依赖审计 | CI 执行 bun audit --audit-level=critical |
独立 shell 脚本使用 moderate 并额外检查许可证/outdated，但未接入 package 命令 |
| coverage | V8 对产品源码执行 80% 全局阈值，显式排除 performance | performance 独立运行，避免插桩与并发负载污染 wall-clock |
| snapshot | 默认测试把现有 .snap 当断言 |
test:update-snapshots 显式传 --update 重写基线 |
Affected Scope
packages/cli/src/tools/builtin/shell/— 有界输出缓冲的内存与 retained chunk 不变量packages/cli/src/utils/KeyedMutexRegistry.ts— 高 churn key 的归零与并发保留上限packages/cli/src/context/— Token 预算和 SQLite/JSONL 投影的性能关注点packages/cli/src/browser/— Chromium sandbox、私有 API 禁用和真实浏览器集成边界packages/cli/scripts/build.ts、packages/cli/web/vite.config.ts— startup 与 Web bundle 测试所需制品的生成入口packages/cli/tests/performance/— 自动 performance project 与可选真实仓库 benchmarkpackages/cli/tests/security/— 安全 smoke、源码契约与输入分类样例packages/cli/tests/snapshots/— 人工批准的字符串输出基线.github/workflows/ci.yml— coverage 前 Chromium 安装、SUID helper、审计与报告上传
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.
- 4d ago First seen · 89 lines · 172 tokens per session scan A 0f42a250e509
knowledge-engineering-quality-and-delivery-performance-security-and-snapshot-gates is a skill published in the GitHub repository echoVic/blade-code (178 stars, last pushed 2d ago), licensed MIT. It adds 172 tokens to every session and 2,534 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
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
tricorder-cli
Full CLI reference for the tricorder daemon (build diagnostics, test results, source lookup, eval comments, logs). This is the fallback invoked by the tricorder skill when the tricorder-mcp MCP tools aren't available or aren't working — invoke tricorder first; it decides whether this is needed.
tricorder-mcp
Check GHCi build status, diagnostics, and test results for this Haskell project via the tricorder MCP server. Use when asked to check the build, see compiler errors/warnings, or run tricorder.
tricorder
Check GHCi build status, compiler errors/warnings, or test results for this Haskell project. Use when asked to check the build, see errors/warnings, or run tricorder.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.