delegate
Hand a coding task to the Deputy sub-agent (DeepSeek V4.1 Flash), which edits files and runs commands itself, then verify its work.
Skill by alimohammadiamirhossein
Chalk Labs
Need help deploying delegate?
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.
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/alimohammadiamirhossein-delegate
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.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo 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/delegate
What's inside
- Skill name
delegate- Description
- Hand a coding task to the Deputy sub-agent (DeepSeek V4.1 Flash), which edits files and runs commands itself, then verify its work. Use when the user says "deputy do X", "delegate", or "/deputy:delegate". In accuracy mode, only when the user explicitly asks.
- License
- MIT
- Instructions
- 26 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Delegate to Deputy
Current Deputy mode: **${user_config.mode}** (if this shows a placeholder, call the `status` tool).
- **accuracy:** write the code yourself. Delegate only because the user asked for it.
- **lean:** delegate well-specified work big enough to pay off (multi-file or repetitive edits,
tests, boilerplate); write changes of a few lines yourself.
- **balanced:** delegate only low-risk mechanical work (boilerplate, renames, formatting, test
scaffolding, repetitive edits). Keep logic and tricky code yourself.
- **partner:** delegate every low-level job, even small ones; keep design and judgment calls
yourself, and read every diff Deputy produces.
- **savings:** delegate well-specified coding work; keep design and risky changes yourself.
## Writing the brief
Put in `task`: the goal, the files or folders in scope, constraints (what not to touch), and how
to verify (a test or build command). Put in `context` facts Deputy cannot discover: decisions
already made, error messages, project conventions. Never include secrets.
## After Deputy finishes
Deputy's "done" is a claim, not proof. Read every changed file it lists, check `git diff`, and run
the tests. Fix small problems yourself. If the result is poor twice in a row, stop delegating and
do the work yourself.
## If the user typed a task after the command
Delegate this task now, following the steps above: $ARGUMENTSFrom alimohammadiamirhossein/deputy, MIT.
More from alimohammadiamirhossein/deputy
- 0.565score
deputy
alimohammadiamirhossein
Playbook for working with Deputy, a cheaper helper model (DeepSeek V4.1 Flash) exposed as MCP tools (consult, review, investigate, delegate).
SkillAFreshness: AClaude Code +9 - 0.565score
review
alimohammadiamirhossein
Have Deputy's cheap reviewers hunt for bugs in your uncommitted change (git diff), then verify each finding yourself.
SkillAFreshness: AClaude Code +9 - 0.559score
consult
alimohammadiamirhossein
Get diverse second opinions from Deputy (DeepSeek V4.1 Flash) with ideas, risks and alternatives, then make the final call yourself.
SkillAFreshness: AClaude Code +9 - 0.559score
investigate
alimohammadiamirhossein
Send a reading-heavy question to Deputy (read-only) and get file:line leads, instead of reading many files yourself.
SkillAFreshness: AClaude Code +9 - 0.552score
deputy
alimohammadiamirhossein
Use the Deputy MCP tools for second opinions before decisions (consult), bug reviews of your changes (review) and wide code searches (investigate).
SkillAFreshness: AClaude Code +9 - 0.510score
Deputy
alimohammadiamirhossein
Claude Code helper: DeepSeek V4.1 Flash reviews Claude's code for bugs and gives second opinions
ConnectorAFreshness: ALocalClaude Code +5
Signals
- Stars
- 0
- Forks
- 2
- Open issues
- 2
- Last commit (this folder)
- Oct 24, 2026 (8 days ago)
- Last release
- Oct 24, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from alimohammadiamirhossein
- 0.565score
deputy
alimohammadiamirhossein
Playbook for working with Deputy, a cheaper helper model (DeepSeek V4.1 Flash) exposed as MCP tools (consult, review, investigate, delegate).
SkillAFreshness: AClaude Code +9 - 0.565score
review
alimohammadiamirhossein
Have Deputy's cheap reviewers hunt for bugs in your uncommitted change (git diff), then verify each finding yourself.
SkillAFreshness: AClaude Code +9 - 0.559score
consult
alimohammadiamirhossein
Get diverse second opinions from Deputy (DeepSeek V4.1 Flash) with ideas, risks and alternatives, then make the final call yourself.
SkillAFreshness: AClaude Code +9 - 0.559score
investigate
alimohammadiamirhossein
Send a reading-heavy question to Deputy (read-only) and get file:line leads, instead of reading many files yourself.
SkillAFreshness: AClaude Code +9 - 0.552score
deputy
alimohammadiamirhossein
Use the Deputy MCP tools for second opinions before decisions (consult), bug reviews of your changes (review) and wide code searches (investigate).
SkillAFreshness: AClaude Code +9 - 0.510score
Deputy
alimohammadiamirhossein
Claude Code helper: DeepSeek V4.1 Flash reviews Claude's code for bugs and gives second opinions
ConnectorAFreshness: ALocalClaude Code +5
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 delegate 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.
Cite this page
delegate skill. Agent Mart. https://agentmart.dev/skills/alimohammadiamirhossein-delegate (last updated 2026-10-24)