skill-injector

A tool that selects relevant coding guidance from a large catalogue and adds it to an agent’s instructions. It uses the task, the agent’s role, and the project’s programming languages.

In plain words
What is it for?
Use it when routing tasks to agents or when an agent needs additional guidance during a task.
Why use it?
It reduces the amount of unrelated guidance an agent must read, while still providing general and task-specific rules.

Skill for Claude CodeCodex

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 skills/d3x293/code-crew/skill-injector
Any agent
npx skills add d3x293/code-crew --skill skill-injector
Clone the repo
git clone --depth 1 https://github.com/d3x293/code-crew

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,206 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 $0.00045 $0.01206
Opus 5 $0.00023 $0.00603
Sonnet 5 $0.00009 $0.00241
Haiku 4.5 $0.00005 $0.00121

Measured 2d ago against content hash 28d5dc20302e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-injector 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 2d 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.

skills/skill-injector/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Injector - Smart Skill Selection

Maps task signals to skills from the everything-claude-code catalog and injects only the relevant ones into each agent's prompt. Prevents context bloat by being selective.

When to Activate

  • During task routing (called by task-router skill)
  • When an agent needs additional skill guidance mid-task

Skill Selection Algorithm

Input

  • Task classification (type + complexity) from task-router
  • Agent role being dispatched
  • Project stack from crew-profile.md
  • Skill catalog from crew-skills.json

Selection Rules

Rule 1: Always-Active Skills (injected into every agent) These are universal best practices (kept minimal for token efficiency):

  • context-budget — monitor token consumption (subsumes strategic-compact)
  • verification-loop — verify before claiming done
  • coding-standards — follow project conventions

Note: iterative-retrieval moved to bug-fix task-type skills. search-first moved to feature task-type skills. strategic-compact dropped (redundant with context-budget).

Rule 2: Stack-Specific Skills (based on detected languages)

Stack Skills
JavaScript/TypeScript typescript-patterns, backend-patterns
React react-patterns, react-testing
Next.js nextjs-patterns
Vue vue-patterns, nuxt4-patterns
Python python-patterns
Django django-patterns, django-security, django-tdd
Flask python-patterns
Go golang-patterns
Rust rust-patterns
Java java-patterns, springboot-patterns
Kotlin kotlin-patterns, kotlin-testing
C++ cpp-coding-standards, cpp-testing
C# csharp-testing, dotnet-patterns
Flutter/Dart dart-flutter-patterns
Swift swiftui-patterns, swift-concurrency-6-2
PHP/Laravel php-patterns, laravel-patterns

Rule 3: Task-Type Skills (based on classified task type)

Task Type Skills
bug-fix iterative-retrieval, deep-research, codebase-onboarding
feature architecture-decision-records, agentic-engineering, blueprint, search-first
refactor architecture-decision-records, backend-patterns
test tdd-workflow, e2e-testing, ai-regression-testing
security security-scanning
docs article-writing, documentation-lookup
devops deployment-patterns, docker-patterns, database-migrations, git-workflow
review verification-loop
performance cost-aware-llm-pipeline

Read the full file on GitHub · 130 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. 2d ago First seen · 130 lines · 45 tokens per session scan A 28d5dc20302e

Subscribe to this mod's changes

skill-injector is a skill published in the GitHub repository d3x293/code-crew (13 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,206 once invoked, about $0.0002 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.