benchmark-competitors

A recurring comparison process for an internal AI development system and competing coding tools. It collects current capabilities and produces a table comparing products such as Cursor, Windsurf, Aider, Codex, and Gemini tools.

In plain words
What is it for?
Use it to run a quarterly competitive benchmark, research tool updates, compare features such as parallel sessions and integrations, and record scores in a comparison matrix.
Why use it?
Coding tools change frequently, making memory-based comparisons unreliable. This process gathers current information and highlights where competitors offer capabilities the internal system may lack.

Command for Claude Code

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 commands/stoa-platform/stoa/benchmark-competitors
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 602 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00602
Opus 5 $0.00000 $0.00301
Sonnet 5 $0.00000 $0.00120
Haiku 4.5 $0.00000 $0.00060

Measured 3d ago against content hash 849fd618d3ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

benchmark-competitors scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Notre score audit : `cat .claude/audit-score.txt`
.claude/commands/benchmark-competitors.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Benchmark Competitif IA Factory

Lance un benchmark trimestriel de notre IA Factory vs la concurrence.

Etape 1 : Collecter les donnees

Pour chaque outil, verifie les dernieres features :

Claude Code (notre stack)

  • Version actuelle : claude --version
  • Features : worktrees, agent teams, skills, hooks, subagents, MCP
  • Notre score audit : cat .claude/audit-score.txt

Cursor

Windsurf (Codeium)

Aider

OpenAI Codex CLI

Amazon Q Developer

  • Focus : AWS integration, enterprise features

Google Gemini CLI / Jules

  • Focus : BigQuery integration, workspace integration

Etape 2 : Matrice de comparaison

Produis un tableau :

Capacite STOA IA Factory Cursor Windsurf Aider Codex Score STOA
Sessions paralleles Worktrees + Agent Teams Composer Cascade Multi-fichier Sandbox /5
Governance/Validation Council 2 stages Non Non Non Non /5
CI/CD integration 8 GHA L1-L5 Git Git Git Non /5
MCP/Tools .mcp.json + 5 MCPs Non Non Non Non /5
Cost control Token Observatory Usage tab ? Token counting ? /5
Auto-format PostToolUse hook Built-in Built-in Non Non /5
Verification verify-app agent Non Non Lint Sandbox /5
Analytics Analytics skill Non Non Non Non /5
Veille/Self-improve competitive-watch Non Non Non Non /5

Etape 3 : Recommandations

Liste 3-5 features des concurrents qu'on devrait adopter, avec :

  • Feature description
  • Quel concurrent la fait
  • Effort d'implementation (1h / 1 jour / 1 semaine)
  • Impact estime sur la productivite

Read the full file on GitHub · 64 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. 3d ago First seen · 64 lines · 0 tokens per session scan B 849fd618d3ff

Subscribe to this mod's changes

benchmark-competitors is a command published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 602 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.