Skip to content
Agentmart
Submit a tool

hafez-decompose

Decompose an active project slice into bounded AI work units with explicit ownership, risk, parallelism, file scopes, verification, and worker tiers so a…

Skill by EngMahmoudHafez

IndexedMIT
Write a review

Chalk Labs

Need help deploying hafez-decompose?

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-decompose

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

Decompose an active project slice into bounded AI work units with explicit ownership, risk, parallelism, file scopes, verification, and worker tiers so a strong lead model can delegate safely to helper models.

Use cases: sales

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-decompose

What's inside

Skill name
hafez-decompose
Description
Decompose an active project slice into bounded AI work units with explicit ownership, risk, parallelism, file scopes, verification, and worker tiers so a strong lead model can delegate safely to helper models.
License
MIT
Instructions
49 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Hafez Decompose

Act as the lead planner before implementation when an active slice contains more than one independently
verifiable concern.

Read the active slice, current Git state, architecture policy, serialized paths, gates, and relevant
contracts. Produce a small execution graph rather than a generic checklist.

Persist the result directly into the active slice's `workUnits` array. Use structured objects, not prose strings.

For each work unit record:

- id in `WU-01` form and objective;
- dependency ids;
- risk: low, medium, high;
- worker tier: scout, worker, specialist, or lead;
- access: read-only or write-worktree;
- whether it is parallel-safe;
- allowed paths;
- required verification commands;
- acceptance criteria owned by the unit;
- integration notes for shared contracts/files;
- initial status: `planned`.

Routing rules:

- Use scouts for repository research, impact analysis, test discovery, and contract comparison.
- Use workers for repetitive, local, low-risk implementation with clear tests.
- Use specialists for security-sensitive auth, migrations, concurrency, payment, performance, complex
  framework behavior, or repeated worker failures.
- Keep product decisions, cross-cutting architecture, conflict resolution, shared serialized files,
  final review, and acceptance with the lead.
- Never give two writers overlapping paths.
- Treat project `serializedPaths`, lockfiles, root route registries, generated shared contracts, and
  migration ordering as serialized unless repository evidence proves otherwise.
- Parallelize read-only scouts freely when useful.
- Prefer the smallest unit that can be independently reviewed and verified; do not fragment trivial
  edits into delegation overhead.

After decomposition, run `hafez dispatch-plan` to validate dependencies and scheduling, then
`hafez dispatch --execute` to start the currently ready helper units. Every write result returns through
`hafez-review`; successful scout results and verified writer integrations advance their work-unit
status automatically. Mark lead-owned units with `hafez work-unit-status <WU-ID> --status completed`
when their acceptance criteria are satisfied.

Do not ask the project owner to choose worker allocation, file ownership, test strategy, or other
technical decomposition details that the lead can determine from repository 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 (25 days ago)
Last release
Oct 6, 2026 (26 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

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-decompose 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-decompose?

CallGet help
Cite this page

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