cross-tech-stack-spec-skill

A set of rules for mapping code knowledge across mobile, web, Python, data, worker, script, and mixed-stack projects. It extends a backend-service analysis workflow when work crosses layers such as pages, apps, clients, servers, tasks, or webhooks.

In plain words
What is it for?
Use it to document mixed technology repositories and trace routes or messages across frontend, mobile, backend, jobs, callbacks, bridges, gateways, and similar boundaries.
Why use it?
It helps prevent a backend-only view from missing how other parts of a system connect. It is used only when cross-stack analysis is needed.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/syz-coder/codebase-knowledge-wiki/cross-tech-stack-spec-skill
Clone the repo
git clone --depth 1 https://github.com/SYZ-Coder/codebase-knowledge-wiki

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,343 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01343
Opus 5 $0.00000 $0.00672
Sonnet 5 $0.00000 $0.00269
Haiku 4.5 $0.00000 $0.00134

Measured yesterday against content hash 007baced6820, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cross-tech-stack-spec-skill 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 yesterday.

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.

.cursor/rules/cross-tech-stack-spec-skill.mdc · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross Tech Stack Spec Skill

Use this rule as an extension to backend-service-spec-skill.mdc when one of these is true:

  • the user explicitly asks for cross-tech-stack analysis or mixed-stack mapping
  • the target repository is primarily mobile, H5, web frontend, Python, data, worker, script, or mixed-stack
  • the requested route crosses page, app, client, backend, task, callback, webhook, bridge, gateway, or message boundaries

Do not use this rule by default for ordinary backend-only microservice analysis. In that case, use backend-service-spec-skill.mdc.

Required Skill Source

Before producing artifacts, read the skill source from one of these locations:

  • If this skill library exists in the target project: cross-tech-stack-spec-skill/SKILL.md
  • If copied under a shared skill folder: skills/cross-tech-stack-spec-skill/SKILL.md
  • If cloned as a project-local rule source: ai-skill-lib/cross-tech-stack-spec-skill/SKILL.md
  • Also read backend-service-spec-skill/SKILL.md, skills/backend-service-spec-skill/SKILL.md, or ai-skill-lib/backend-service-spec-skill/SKILL.md because this rule extends the backend service workflow instead of replacing it.

Read only the relevant reference files when they exist:

  • cross-tech-stack-spec-skill/references/mobile-project-guidelines.md
  • cross-tech-stack-spec-skill/references/h5-project-guidelines.md
  • cross-tech-stack-spec-skill/references/python-project-guidelines.md
  • cross-tech-stack-spec-skill/references/mixed-stack-routing-guidelines.md
  • cross-tech-stack-spec-skill/references/workspace-layering-template.md
  • cross-tech-stack-spec-skill/references/mixed-stack-noise-exclusion-guide.md
  • cross-tech-stack-spec-skill/references/interface-mapping-template.md
  • cross-tech-stack-spec-skill/references/communication-matrix-guidelines.md
  • cross-tech-stack-spec-skill/references/communication-evidence-levels.md
  • cross-tech-stack-spec-skill/references/mixed-stack-domain-mapping-guidelines.md
  • cross-tech-stack-spec-skill/references/incremental-update-mode.md
  • cross-tech-stack-spec-skill/references/activation-and-boundaries.md
  • cross-tech-stack-spec-skill/references/diagram-output-guidelines.md
  • cross-tech-stack-spec-skill/references/mermaid-safety-checklist.zh-CN.md

Read the full file on GitHub · 144 lines

Changes

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.

  1. yesterday First seen · 144 lines · 0 tokens per session scan A 007baced6820

Subscribe to this mod's changes

cross-tech-stack-spec-skill is a cursor rule published in the GitHub repository SYZ-Coder/codebase-knowledge-wiki (9 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,343 tokens. 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 2026-08-31.