Skip to content
Agentmart
Submit a tool

hafez-debug

Diagnose and repair reproducible project failures continuously using evidence-first debugging, regression tests, bounded delegation, and repeated verification…

Skill by EngMahmoudHafez

IndexedMIT
Write a review

Chalk Labs

Need help deploying hafez-debug?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/engmahmoudhafez-hafez-debug

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Diagnose and repair reproducible project failures continuously using evidence-first debugging, regression tests, bounded delegation, and repeated verification until the failure is fixed or a genuine external decision is required.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/hafez-debug

What's inside

Skill name
hafez-debug
Description
Diagnose and repair reproducible project failures continuously using evidence-first debugging, regression tests, bounded delegation, and repeated verification until the failure is fixed or a genuine external decision is required.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Hafez Debug

Use this skill when a required gate, test, build, runtime check, migration, integration contract, or repeatable project command fails.

Do not stop at the first error message.

1. Reproduce the failure with the narrowest deterministic command.
2. Capture the actual failing output and identify the first causal error, not downstream noise.
3. Inspect nearby code, recent Git changes, configuration, lockfiles, and relevant tests.
4. Form one concrete root-cause hypothesis at a time.
5. For independent investigation, delegate read-only scouts to helper models in parallel.
6. For a narrow repair, delegate one isolated writer when useful; the lead remains responsible for review.
7. Make the smallest safe change that addresses the root cause.
8. Add or strengthen a regression test when the defect can recur.
9. Re-run the narrow reproduction, then the required project gates.
10. If the worker repair fails review, reject it and issue a narrower repair task.
11. Update Hafez evidence/state and return to `hafez-autopilot`.

Never:
- disable or weaken a required test merely to make CI green;
- convert skipped/unavailable checks into success;
- hide an error with a broad catch or ignore rule without proving that behavior is intended;
- ask the user to choose an implementation detail that repository evidence can resolve safely.

Escalate only for a genuine product/architecture choice, missing credentials or external authority, destructive action, or a failure that cannot be reproduced with available evidence.

From EngMahmoudHafez/hafez-development-system, MIT.

More from EngMahmoudHafez/hafez-development-system

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 7, 2026 (24 days ago)
Last release
Oct 6, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/EngMahmoudHafez/hafez-development-system
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from EngMahmoudHafez

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get hafez-debug running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying hafez-debug?

CallGet help
Cite this page

hafez-debug skill. Agent Mart. https://agentmart.dev/skills/engmahmoudhafez-hafez-debug (last updated 2026-10-24)