subagent
Plan a task, get user approval, then delegate execution to a Herdr pi sub-agent (defaults to openrouter/meta/muse-spark-1.3 at xhigh thinking; override with…
Skill by silacode
Chalk Labs
Need help deploying subagent?
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/silacode-subagent
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
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/subagent
What's inside
- Skill name
subagent- Description
- Plan a task, get user approval, then delegate execution to a Herdr pi sub-agent (defaults to openrouter/meta/muse-spark-1.3 at xhigh thinking; override with --model); verify its work independently and either close it or send fix-up instructions (max 3 rounds). YOLO mode (leading `yolo` argument) answers the sub-agent's questions instead of relaying them. Use when the user asks to delegate, hand off, or run a task through a sub-agent. Requires HERDR_ENV=1.
- License
- unknown
- Metadata
- argument-hint: [yolo] [--model <provider/id[:thinking]>] [--thinking <level>] <task>
- Instructions
- 120 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- subagent.sh · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from silacode/agent-skills
- 0.561score
new-workspace
silacode
Create or safely close a Herdr workspace backed by a git worktree (nested under the repo workspace), including workspace-ID labels, pane cleanup, worktree…
SkillAFreshness: AClaude Code +9 - 0.561score
typescript-best-practices
silacode
Apply when reading, writing, or reviewing TypeScript (.ts/.tsx), especially when designing types or function signatures or handling external data.
SkillAFreshness: AClaude Code +9 - 0.559score
security-alerts-plan
silacode
Fetch all of the repository's open GitHub security alerts (Dependabot, code scanning, secret scanning, and repository security advisories), trace each to its…
SkillAFreshness: AClaude Code +9 - 0.559score
review-comment-triage
silacode
Classify review-bot comments (CodeRabbit, Copilot, Greptile, Sentry) using only TRUE, TRUE-MINOR, or FALSE, with a one-line argument each.
SkillAFreshness: AClaude Code +9 - 0.556score
how
silacode
Explain how code works: runtime flow, subsystem architecture, walkthroughs before a change, and where new code should live (which module or layer owns it).
SkillAFreshness: AClaude Code +9 - 0.551score
sharpen
silacode
Sharpen a task before starting: find the real goal and the expert approach, keep explicit requirements, ask only blocking questions, and pick an independent…
SkillAFreshness: AClaude Code +9 - 0.551score
principle-test-behavior-not-implementation
silacode
Apply when you write, change, review, or keep a test.
SkillAFreshness: AClaude Code +9 - 0.531score
principle-boundary-discipline
silacode
Apply when wiring validation, error handling, or framework adapters.
SkillAFreshness: AClaude Code +9 - 0.526score
principle-encode-lessons-in-structure
silacode
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 15, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/silacode/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from silacode
- 0.561score
new-workspace
silacode
Create or safely close a Herdr workspace backed by a git worktree (nested under the repo workspace), including workspace-ID labels, pane cleanup, worktree…
SkillAFreshness: AClaude Code +9 - 0.561score
typescript-best-practices
silacode
Apply when reading, writing, or reviewing TypeScript (.ts/.tsx), especially when designing types or function signatures or handling external data.
SkillAFreshness: AClaude Code +9 - 0.559score
security-alerts-plan
silacode
Fetch all of the repository's open GitHub security alerts (Dependabot, code scanning, secret scanning, and repository security advisories), trace each to its…
SkillAFreshness: AClaude Code +9 - 0.559score
review-comment-triage
silacode
Classify review-bot comments (CodeRabbit, Copilot, Greptile, Sentry) using only TRUE, TRUE-MINOR, or FALSE, with a one-line argument each.
SkillAFreshness: AClaude Code +9 - 0.556score
how
silacode
Explain how code works: runtime flow, subsystem architecture, walkthroughs before a change, and where new code should live (which module or layer owns it).
SkillAFreshness: AClaude Code +9 - 0.551score
sharpen
silacode
Sharpen a task before starting: find the real goal and the expert approach, keep explicit requirements, ask only blocking questions, and pick an independent…
SkillAFreshness: AClaude Code +9
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 subagent 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
subagent skill. Agent Mart. https://agentmart.dev/skills/silacode-subagent (last updated 2026-10-24)