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 agentmods add skills/jordancoin/codingskills/detect-stacknpx skills add JordanCoin/codingskills --skill detect-stackgit clone --depth 1 https://github.com/JordanCoin/codingskillsWhat 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 | $0.00063 | $0.00746 |
| Opus 5 | $0.00032 | $0.00373 |
| Sonnet 5 | $0.00013 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
detect-stack 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detect Stack
Analyze the current codebase and generate .agents/stack-context.md. Run this on first use in a project, or when the stack context is missing or stale.
What to Detect
Scan the project root for these signals:
Language — Count file extensions (.rs, .py, .ts, .go, .swift, .java, .rb, .cs, .ex, etc.). Primary = most files. Note secondary languages.
Framework — Read the package manifest:
Cargo.toml→ check[dependencies]for axum, actix, rocket, sqlx, diesel, tokiopackage.json→ check for react, next, svelte, express, fastify, prismago.mod→ check for gin, echo, fiber, chi, sqlcpyproject.toml/requirements.txt→ check for django, flask, fastapi, sqlalchemyGemfile→ check for rails, sinatraPackage.swift→ check for Vapor; scan for SwiftUI importsmix.exs→ check for phoenix, ecto
Tests — Look for test directories, test file naming patterns, test config files.
CI gates — Scan .github/workflows/, .gitlab-ci.yml, etc. for blocking checks (format, lint, type check, test).
Conventions — Check for CLAUDE.md, AGENTS.md, CONTRIBUTING.md. Note directory structure and naming patterns.
Output
Write .agents/stack-context.md — keep it short (under 40 lines):
# Stack Context
Generated: YYYY-MM-DD
## Stack
- **Language**: [primary] [version if pinned]
- **Framework**: [web framework], [db layer]
- **Build**: [build tool]
- **Test**: [test command + framework]
- **Lint**: [linter] [CI gate: yes/no]
- **Format**: [formatter] [CI gate: yes/no]
## Secondary Languages
- [language] ([what it's used for])
## Conventions
- Error handling: [pattern]
- Module structure: [pattern]
- Naming: [pattern]
- Tests: [where they live, how they're organized]
## CI Gates
- [list of blocking checks]
Stack-Specific Principle Application
After writing the stack context, do not generate static reference files. Instead:
- Use your built-in knowledge of the detected language/framework to apply each coding principle idiomatically
- If you need specific framework API details, use context7 MCP (
resolve-library-idthenquery-docs) to pull live documentation - If context7 doesn't cover it, use web search as fallback
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.
- 2d ago First seen · 79 lines · 63 tokens per session scan A 2d6d3fc9d8ab
detect-stack is a skill published in the GitHub repository JordanCoin/codingskills (7 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 746 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
refactor
Automated iterative code refactoring with swarm-orchestrated specialist agents including deep codebase discovery, confidence-scored code review, and security analysis. Use this skill when the user wants to improve existing code quality, clean up messy code, restructure, simplify, reduce tech debt, or perform…
refactoring
Improve code structure without changing behavior using proven refactoring patterns. Use when cleaning up code, reducing duplication, improving readability, or restructuring modules.
feature-dev
Guided feature development with swarm-orchestrated codebase exploration, multi-perspective architecture design, implementation, and quality review.
feature-dev
Guided feature development with swarm-orchestrated codebase exploration, multi-perspective architecture design, implementation, and quality review. Use this skill when the user wants to build a new feature, add new functionality, implement a capability, or create something that doesn't exist yet. Triggers on requests…
refactoring-patterns
Use this skill when improving existing code without changing its behavior. It defines when and how to refactor safely.
delphi-rest-apis-horse
Desenvolvimento de microserviços e APIs REST com o framework minimalista Horse em Delphi. Rotas, controllers, middlewares, gerenciamento de memória e tratamento de parâmetros.