agentmods.dev

spec-injection-index

A routing rule set that selects project specifications based on the kind of coding task being done. It also defines specifications that must always be loaded, such as verification rules.

In plain words
What is it for?
Use it at the start of repository tasks to choose specifications for areas such as security, commands, agents, APIs, Python SDKs, documentation, or mixed work.
Why use it?
It prevents implementation work from starting with the wrong instructions or missing required project rules.

Cursor rule for Cursor

167 +1 7d ago A scan 374 tokens original MIT
View the source file EXboys/skilllite
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/exboys/skilllite/spec-injection-index
Clone the repo
git clone --depth 1 https://github.com/EXboys/skilllite

Made for: Cursor.

Per session 374 This file is loaded in full into every session.
When invoked 374 The same file — it is already loaded in full.
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 $0.00374 $0.00374
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 3d ago against content hash be53e69c8929, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-injection-index 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 3d 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.

.cursor/rules/spec-injection-index.mdc · 41 lines

What it actually says

Spec Injection Router

spec/ + tasks/ apply to developing this repo, not to end-user or shipped-app runtime configuration (see Repository scope in spec/README.md).

Before implementation, load spec/README.md and choose injected specs using its mapping and deterministic rules.

Required Workflow

  1. Always inject spec/verification-integrity.md first — this is the highest-priority spec and applies unconditionally.
  2. Always inject spec/task-artifact-language.md for task execution records (tasks/TASK-.../*).
  3. Determine task type:
    • architecture, security, sandbox, agent, commands, mcp, python-sdk, docs-only, or mixed.
  4. Build [Injected Specs] from spec/README.md.
  5. Follow all MUST / MUST NOT / CHECKLIST items in each injected spec.
  6. If multiple mappings match, inject all matched specs.
  7. For any Rust code change, always include spec/rust-conventions.md and spec/testing-policy.md.
  8. If user-visible behavior, env vars, commands, architecture docs, or release matrix change, include spec/docs-sync.md.

Output Convention

At task start, explicitly declare:

[Injected Specs]
- spec/<file-a>.md
- spec/<file-b>.md
...

At task end, confirm:

  • spec/verification-integrity.md checklist was completed (anti-hallucination, anti-false-positive),
  • which specs were injected,
  • which checklists were completed,
  • which verification commands were run (with actual output, not model assertions).
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. 3d ago First seen · 41 lines · 374 tokens per session scan A be53e69c8929

Subscribe to this mod's changes

spec-injection-index is a cursor rule published in the GitHub repository EXboys/skilllite (167 stars, last pushed 7d ago), licensed MIT. It adds 374 tokens to every session, about $0.0019 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.

agentskillsai-agentsrust-sandboxsandboxself-evolving
Related

Other cursor rules, from other repositories

global

Cursor rule "global" from KroMiose/nekro-agent, covering 项目背景（简要）, 开发规范, 文档, 开发指南 and 功能/页面开发完整流程.

KroMiose/nekro-agent · 669 tokens

ai-actions-schemas

Cursor rule "ai-actions-schemas" from freshworks-developers/fw-dev-tools, covering ai actions schemas (actions.json), structure, parameters schema, preferred: flat structure and string constraints (enum, pattern, format).

freshworks-developers/fw-dev-tools · 0 tokens

frontend-rules

前端 React 服务开发指南.

KroMiose/nekro-agent · 0 tokens

cognitive-principle-check

新知识原则校验规则：向L1文档写入新内容后，自动检查是否与L1.5已确认原则（P1/P2等）存在张力。当向认知结构L1文档写入新内容时自动激活。.

TashanGKD/tashan-cursor-skills · 57 tokens

cursorrules

Load CONVENTIONS.md for stack defaults. Load router.md for skill routing. 14 categories (01-14), 94 reference docs, 18 agents.

heymegabyte/claude-skills · 193 tokens

cognitive-insight-guard

洞见守卫。每条用户消息后，语义判断是否包含视角纠正、本质澄清、设计原则等认知价值内容。检测到时在回复末尾轻量提示是否沉淀。.

TashanGKD/cognitive-os · 327 tokens