HERO-Anti-OverDefense

HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.

wanshuiyin/HERO-Anti-OverDefense

View on GitHub ↗

HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.

HERO-Anti-OverDefense grew +71.8% in the last 30 days, ranks 266th of 1,105 in Prompting & Scaffolding, actively maintained, last commit 3 days ago.

Star trajectory

82 days tracked
2026-08-31888 stars today2026-11-22
Momentum

+71.8% in 30d, above the Prompting & Scaffolding median of +1.5%.

Maintenance

Last commit 3 days ago, fresher than the median of 35d.

How it compares in Prompting & Scaffolding

HERO-Anti-OverDefense
888
stars
+71.8% 30d
commit 3 days ago
Prompting & Scaffolding median
319
stars
+1.5% 30d
commit ~35d ago
Leader · ponytail
196.6k
stars
+13.0% 30d
commit today

Ranked 266th of 1,105 by stars.

Ranked by shared tags, then keywords, then stars
  1. Deterministic prose checks for clearer coding-agent responses

    +6 (+2.0%) in 30d · Committed 94d ago · TypeScript · MIT

    Shares Prompting & Scaffolding, Evaluation & Guardrails

  2. Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review…

    +23 (+11%) in 30d · Committed 9d ago · Python · MIT

    Shares Prompting & Scaffolding, Evaluation & Guardrails

  3. Stop hooks that stop AI coding agents (Claude Code, Codex) from claiming "done" without proof. A Lean quality…

    +3 (+1.8%) in 30d · Committed yesterday · Python · MIT

    Shares Evaluation & Guardrails, Prompting & Scaffolding

  4. Rules for an AI coding agent to filter out generic AI-generated UI designs, text, and code.

    +2.9k (+42%) in 30d · Committed yesterday · JavaScript · MIT

    Shares Prompting & Scaffolding, Evaluation & Guardrails

  5. J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work…

    -15 (-0.5%) in 30d · Committed 69d ago · Python · Apache-2.0

    Shares Prompting & Scaffolding, Evaluation & Guardrails

  6. The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that…

    +19 (+0.8%) in 30d · Committed 50d ago · Python · MIT

    Shares Prompting & Scaffolding, Evaluation & Guardrails

  7. Enterprise architecture governance for Claude Code and other AI coding assistants. 76 commands draft…

    +23 (+1.0%) in 30d · Committed 2d ago · JavaScript · Other license

    Shares Evaluation & Guardrails, Prompting & Scaffolding

  8. Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and…

    +28 (+2.3%) in 30d · Committed 224d ago · Python

    Shares Prompting & Scaffolding, Evaluation & Guardrails

  9. Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an…

    Committed 13d ago · MIT

    Shares Evaluation & Guardrails, Prompting & Scaffolding

  10. AI writing skill that eliminates detectable AI patterns. Works with Claude Code, Codex, Cursor, Gemini CLI…

    +62 (+11%) in 30d · Committed 217d ago

    Shares Prompting & Scaffolding, Evaluation & Guardrails

Language
Python
License
MIT License
Contributors
3
Forks
32
Watchers
0
Open issues
1
Releases
0
Created
2026-08-11
Stars this week
+33

You've seen where HERO-Anti-OverDefense stands today.

Get the moves before everyone else: the 5 Prompting & Scaffolding repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain HERO-Anti-OverDefense?

Claim this page to add your own call-to-action.

Claim this page