cypher0n3/dotagents
Opinionated, portable agent skills and instructions with installer script for Claude Code, Codex, Cursor, Gemini, and Grok. One directory (~/.agents), installed by symlink.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit cypher0n3/dotagents/agents ./rig-dotagents/agents $ npx degit cypher0n3/dotagents/skills ./rig-dotagents/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit cypher0n3/dotagents/skills/agent-feedback .claude/skills/agent-feedback $ npx degit cypher0n3/dotagents/skills/code-review-precision .claude/skills/code-review-precision $ npx degit cypher0n3/dotagents/skills/detailed-execution-planner .claude/skills/detailed-execution-planner $ npx degit cypher0n3/dotagents/skills/docs-only-convo .claude/skills/docs-only-convo $ npx degit cypher0n3/dotagents/skills/feature-files-authoring .claude/skills/feature-files-authoring $ npx degit cypher0n3/dotagents/skills/go-developer .claude/skills/go-developer $ npx degit cypher0n3/dotagents/skills/grill-me .claude/skills/grill-me $ npx degit cypher0n3/dotagents/skills/herdr .claude/skills/herdr $ npx degit cypher0n3/dotagents/skills/just-ci .claude/skills/just-ci $ npx degit cypher0n3/dotagents/skills/make-commit .claude/skills/make-commit $ npx degit cypher0n3/dotagents/skills/make-meta-commit .claude/skills/make-meta-commit $ npx degit cypher0n3/dotagents/skills/markdown-writer .claude/skills/markdown-writer $ npx degit cypher0n3/dotagents/skills/merge-prep .claude/skills/merge-prep $ npx degit cypher0n3/dotagents/skills/promote-specs-losslessly .claude/skills/promote-specs-losslessly $ npx degit cypher0n3/dotagents/skills/python-test-automation .claude/skills/python-test-automation $ npx degit cypher0n3/dotagents/skills/requirements-authoring .claude/skills/requirements-authoring $ npx degit cypher0n3/dotagents/skills/senior-developer .claude/skills/senior-developer $ npx degit cypher0n3/dotagents/skills/senior-go-dev-reviewer .claude/skills/senior-go-dev-reviewer $ npx degit cypher0n3/dotagents/skills/spec-authoring .claude/skills/spec-authoring $ npx degit cypher0n3/dotagents/skills/strip-ai-tells .claude/skills/strip-ai-tells $ npx degit cypher0n3/dotagents/skills/tech-specs-update .claude/skills/tech-specs-update $ npx degit cypher0n3/dotagents/skills/update-cursor-todos .claude/skills/update-cursor-todos
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/docs-writer.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/docs-writer.md $ curl -fsSL --create-dirs -o .claude/agents/feature-author.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/feature-author.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer-go.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/reviewer-go.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-author.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/spec-author.md $ curl -fsSL --create-dirs -o .claude/agents/test-runner.md https://raw.githubusercontent.com/cypher0n3/dotagents/main/agents/test-runner.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (22)
agent-feedbackcode-review-precisiondetailed-execution-plannerdocs-only-convofeature-files-authoringgo-developergrill-meherdrjust-cimake-commitmake-meta-commitmarkdown-writermerge-preppromote-specs-losslesslypython-test-automationrequirements-authoringsenior-developersenior-go-dev-reviewerspec-authoringstrip-ai-tellstech-specs-updateupdate-cursor-todos
Subagents (9)
| coder model: opus | Implements one scoped change end to end, with tests, and proves it against the repository's own checks. Use this agent when a task is defined well enough to hand off as a unit of implementation work. |
| docs-writer model: sonnet | Writes, revises, and audits Markdown documentation against the conventions of the repository it is running in, and leaves every file it touches passing that repository's lint. Use this agent when a RE |
| feature-author model: sonnet | Writes and revises Gherkin feature files that trace to the repository's requirements and specifications, then lints them. Use this agent when business scenarios need to be captured or updated as featu |
| planner model: opus | Turns a task into a detailed, test-gated execution plan as a Markdown checklist grounded in the repository's requirements and specifications. Use this agent when work needs a written implementation se |
| researcher model: sonnet | Gathers facts from the repository, its documentation, and the web, and reports them with exact references, without making any changes. Use this agent when a question needs evidence collected from many |
| reviewer-go model: opus | Performs adversarial review of a Go change against its specifications, modern Go practice, concurrency and security risks, and the repository's own checks, without editing anything. Use proactively af |
| reviewer model: opus | Performs adversarial review of a code change in any language against its specifications, the repository's conventions, and its own lint and test gates, without editing anything. Use proactively after |
| spec-author model: sonnet | Writes and revises requirements and technical specifications to the repository's own documentation standards, then lints them. Use this agent when a change needs its requirements or technical specific |
| test-runner model: sonnet | Runs a repository's tests, diagnoses each failure down to a root cause, and writes or repairs tests when the task calls for it. Use this agent when a change needs its tests run, when a failing or flak |
Similar rigs
juzser/blacksmith
Autonomous agent factory — loop runner, worktree engine, and a local dashboard over the event log.
Orchestrator 2.6k tok ·
OMOCHInoHOSHI/dotfiles-claude
.claude
Pragmatist 293 tok ·
BillDX/spicy-to-dark-factory-starter
Workshop starter for 'From Spicy Autocomplete to Dark Factory: Agentic Coding in Practice' — a FastAPI mini-app with a full Claude Code harness (agents, slash commands, hooks, sandbox settings) and self-paced exercises.
Orchestrator 706 tok ·
blueclover22/mw_agent_kit
Spec-driven development workflow for Claude Code — built around an approved design doc, where each stage waits for your approval.
Orchestrator 2.9k tok ·