Skip to content
Skills Library
Programming · Planning

ai-coding-tools-stinger

/ai-coding-tools-stinger

Choose, configure or troubleshoot AI coding tools, and write bounded task briefs. Use for tool comparison, prompt context, task scope, acceptance, ownership and verification.

Licence
AGPL-3.0
Last repository change
14.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
24
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 14.10.2026, without references to retired models or APIs.

Licence

AGPL-3.0, copyleft: przeróbki udostępniane innym muszą mieć tę samą licencję.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: references/examples/task-briefs/fixtures/invoice-handler.ts

What it does and when to use it

Choose, configure or troubleshoot AI coding tools, and write bounded task briefs. Use for tool comparison, prompt context, task scope, acceptance, ownership and verification.

Original author description

Choose, configure or troubleshoot AI coding tools, and write bounded task briefs. Use for tool comparison, prompt context, task scope, acceptance, ownership and verification.

How it works

  1. When to use this skill
  2. Purpose
  3. Critical directives (non-negotiables)
  4. When to use each guide
  5. Tool tier quick-reference (2026)
  6. Overlap boundaries
  7. Guides index
  8. Examples
  9. Templates
  10. Reports
Original SKILL.md headings · 106 lines, 941 words
SKILL.md preview
---
name: "ai-coding-tools-stinger"
description: "Choose, configure or troubleshoot AI coding tools, and write bounded task briefs. Use for tool comparison, prompt context, task scope, acceptance, ownership and verification."
license: AGPL-3.0-or-later
---

# AI Coding Tools Stinger

## When to use this skill

Covers the vibe-coder's AI coding tool landscape: Cursor, Claude Code, Aider, Cline, Windsurf/Cascade, Continue.dev, Replit Agent, Devin, and Bolt. Covers tool-tier classification, the selection rubric (autonomy, context, budget, language), SWE-bench benchmark data, model-routing patterns (including Aider's 3-5x cost-reducing architect/editor split), per-tool prompt and context discipline, and a documented footgun catalog.

Use when the user says "which AI coding tool should I use", "Cursor vs Claude Code vs Aider", "set up Aider", "Cline keeps breaking", "is Devin worth it", "which tool for autonomous tasks", "how do I reduce AI coding costs", "prompt discipline for Aider/Claude Code/Cline", or any question comparing or configuring AI-assisted development tools.

Cross-links to cursor-ide-wasp-drone for deep Cursor IDE config and ai-tools-platform-wasp-drone for LLM provider/gateway decisions. Do NOT use for Cursor IDE configuration (cursor-ide-wasp-drone owns that), CI/CD pipelines that run agents (devops-wasp-drone), or LLM provider gateway architecture beyond tool-specific routing (ai-tools-platform-wasp-drone).

For "Help me write a clear coding request", "Prepare a bounded worker brief" or "What context should I give an AI coding assistant?", read [the task brief guide](guides/07-write-a-bounded-task-brief.md) and use [the template](templates/task-brief.md). Preserve actual context, authority, acceptance, ownership, inherited settings, budget, checks and stopping conditions. App Primer owns capacity and wave preparation; Harness Integration owns host availability.

## Purpose

This Stinger equips `ai-coding-tools-wasp-drone` to recommend, compare, configure, and debug AI coding tools across the 2026 ecosystem. Every factual claim in this skill traces to a source research note (source-repository research, not shipped with the plugin); the shipped `research/research-summary.md`, where present, carries the conclusions.

The Stinger is organized around the tool guides and the bounded task brief guide that mirror the Drone's ACTION list. Read the guide that matches the user's question. All guides reference each other and cite their research sources.

---

## Critical directives (non-negotiables)

- **Always cite the benchmark source and date.** SWE-bench scores change monthly. Every capability claim must include `(SWE-bench Verified, retrieved 2026-05-20)` or an equivalent dated citation. See `guides/02-benchmark-data.md`.

- **Windsurf is owned by Cognition AI, NOT OpenAI.** OpenAI announced a $3B acquisition in May 2025, Microsoft blocked it in July 2025, then Cognition AI (makers of Devin) acquired Windsurf for ~$250M in December 2025. All guides must reflect Cognition AI ownership. Source: `research/external/2026-05-20-windsurf-cursor-2026.md` (source-repository research, not shipped with the plugin).

- **Cross-link to `cursor-ide-wasp-drone` for any Cursor IDE configuration request.** Deep Cursor config (rules, MCP servers, Cloud Agents, SDK) is out of scope for this Stinger.

- **Never recommend Devin or Replit Agent for production repos without flagging autonomy risks.** Fully-autonomous tools have write access and may make sweeping changes without user review. Surface the risk before opting in.

- **State the model-routing default explicitly.** Tool defaults change. Claude Code uses Claude (subscription or API). Aider supports 100+ models. Cursor routes to multiple providers. Windsurf uses its own Cascade model plus third-party routing. Verify before advising.

---

## When to use each guide

| User question | Guide |
|---------------|-------|
| "Which tier is this tool?" / "What's the difference?" | `guides/00-tool-tiers.md` |
| "Which tool fits my workflow?" | `guides/01-selection-rubric.md` |
| "What are the benchmark scores?" / "How good is X?" | `guides/02-benchmark-data.md` |
| "Which LLM should I use with Aider?" / "How does Cursor route?" | `guides/03-model-routing.md` |
| "How do I structure CLAUDE.md?" / ".aider.conf.yml setup" | `guides/04-prompt-and-context-discipline.md` |
| "Cline keeps failing" / "Aider auto-committed bad code" | `guides/05-footguns.md` |
| "Can I use Cursor AND Claude Code together?" | `guides/06-multi-tool-stacking.md` |

---

## Tool tier quick-reference (2026)

| Tier | Tools | Best for |
|------|-------|---------|
| Interactive-pair | Cursor (Tab + Composer), Continue.dev | Editor-integrated pair programming, in-flow completions |
| Hybrid-agent | Claude Code, Aider, Cline, Windsurf (Cascade) | Terminal/sidebar autonomous tasks with human in the loop |
| Fully-autonomous | Devin 2.0, Cursor Background Agents | Unattended long-running tasks; high autonomy tolerance required |
| Rapid-scaffold | Bolt.new, Replit Agent | Greenfield app generation from prompt; WebContainer or cloud IDE |

Cursor uniquely spans interactive-pair AND hybrid-agent (Agent Mode). See `guides/00-tool-tiers.md` for the full taxonomy.

---

## Overlap boundaries

- **`cursor-ide-wasp-drone`**: owns Cursor IDE configuration depth: `.cursor/rules/` authoring, MCP server registration, Cloud Agents, Background Agents configuration, `@cursor/sdk` API. Cross-link there for anything beyond tool selection.
- **`ai-tools-platform-wasp-drone`**: owns the LLM provider/gateway layer: Portkey, OpenRouter, Bedrock, Vertex AI, cost optimization across providers. This Stinger covers tool-specific model routing only (e.g., Aider's `--architect` flag, Claude Code's model lock-in).
- **`devops-wasp-drone`**: owns CI/CD pipelines that invoke agents (GitHub Actions running Devin, cron jobs running Aider). This Stinger covers tool selection and configuration; not pipeline topology.

---

## Guides index

- `guides/00-tool-tiers.md`: Four-tier taxonomy with all 2026 tools mapped
- `guides/01-selection-rubric.md`: Decision matrix: autonomy, context, budget, language axes
- `guides/02-benchmark-data.md`: SWE-bench Verified and Aider polyglot scores (dated 2026-05-20)
- `guides/03-model-routing.md`: Default LLM per tool, override patterns, Aider architect/editor split
- `guides/04-prompt-and-context-discipline.md`: CLAUDE.md, `.aider.conf.yml`, Cursor rules, per-tool best practices
- `guides/05-footguns.md`: Cline reliability issues, Aider auto-commit, Devin scope creep, Bolt limits
- `guides/06-multi-tool-stacking.md`: Combining tools (e.g., Cursor for interactive + Claude Code for batch)

- `guides/07-write-a-bounded-task-brief.md`: A tool-neutral request and bounded handoff with explicit authority and evidence

## Examples

- `examples/happy-path-selection.md`: Senior dev, TypeScript monorepo, hybrid workflow
- `examples/cost-constrained-workflow.md`: Solo founder, API budget constraint, Aider architect/editor

- `examples/bounded-brief.md`: Permission-boundary review with the missing implementation retained as unknown
- `examples/vague-request-repair.md`: Narrow an ambiguous request before implementation
- `examples/coordination-handoff.md`: Preserve unresolved acceptance, ownership and capacity

## Templates

- `templates/tool-recommendation.md`: Reusable output template for inline recommendations

- `templates/task-brief.md`: Context, acceptance, exclusive scope, authority, checks and stopping conditions

## Reports

- `reports/README.md`: How past recommendation audits accumulate here

---

*Command Brief: `ai-tools/command-briefs/ai-coding-tools-wasp-drone-command-brief.md`*
*Research: `research/research-summary.md` | Depth: normal | Retrieved: 2026-05-20*
Files in this package (24)
  • README.md 2 KB
  • SKILL.md 8 KB
  • examples/bounded-brief.md 3 KB
  • examples/coordination-handoff.md 1 KB
  • examples/cost-constrained-workflow.md 4 KB
  • examples/happy-path-selection.md 3 KB
  • examples/vague-request-repair.md 1 KB
  • guides/00-tool-tiers.md 7 KB
  • guides/01-selection-rubric.md 4 KB
  • guides/02-benchmark-data.md 4 KB
  • guides/03-model-routing.md 5 KB
  • guides/04-prompt-and-context-discipline.md 7 KB
  • guides/05-footguns.md 7 KB
  • guides/06-multi-tool-stacking.md 6 KB
  • guides/07-write-a-bounded-task-brief.md 4 KB
  • references/examples/task-briefs/evidence/qualification.json 1 KB
  • references/examples/task-briefs/evidence/request-ledger.json 4 KB
  • references/examples/task-briefs/evidence/semantic-review.md 2 KB
  • references/examples/task-briefs/fixtures/invoice-handler.ts 1 KB
  • references/examples/task-briefs/fixtures/requests.md 1 KB
  • reports/README.md 1 KB
  • research/research-summary.md 7 KB
  • templates/task-brief.md 2 KB
  • templates/tool-recommendation.md 2 KB

Versions

The database has no other skills named ai-coding-tools-stinger.

Database snapshot: 13.11.2026 · package version 4d7746c56164 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 1 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100knowledge-stinger
    Write narrative knowledge docs for a repository. Use for architecture overviews, diagrams, auth flows, schema references, or coding standards. Read README.md for the guide map.
  • 100readme-writing-stinger
    Write and audit README files as landing pages. Use for value proposition, install flow, badges, structure, or internal tool context. Read README.md for the guide map.
  • 100coding-standards
    Use when writing, updating, or auditing CODING_STANDARDS.md, or when a mistake from a session or review should become a coding rule.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.