Gord1y/countersign-skills
Agent Skills, global rules and subagents for Claude Code, Codex and Antigravity, with one installer.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit Gord1y/countersign-skills/agents ./rig-countersign-skills/agents $ npx degit Gord1y/countersign-skills/skills ./rig-countersign-skills/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 Gord1y/countersign-skills/skills/codebase-research .claude/skills/codebase-research $ npx degit Gord1y/countersign-skills/skills/context-transfer .claude/skills/context-transfer $ npx degit Gord1y/countersign-skills/skills/feature-pr-description .claude/skills/feature-pr-description $ npx degit Gord1y/countersign-skills/skills/how-it-works .claude/skills/how-it-works $ npx degit Gord1y/countersign-skills/skills/human-voice-writing .claude/skills/human-voice-writing $ npx degit Gord1y/countersign-skills/skills/i18n-translate .claude/skills/i18n-translate $ npx degit Gord1y/countersign-skills/skills/impact-check .claude/skills/impact-check $ npx degit Gord1y/countersign-skills/skills/memory-review .claude/skills/memory-review $ npx degit Gord1y/countersign-skills/skills/orchestrate .claude/skills/orchestrate $ npx degit Gord1y/countersign-skills/skills/pr-review-triage .claude/skills/pr-review-triage $ npx degit Gord1y/countersign-skills/skills/promotion-pr-description .claude/skills/promotion-pr-description $ npx degit Gord1y/countersign-skills/skills/qa-tester .claude/skills/qa-tester $ npx degit Gord1y/countersign-skills/skills/release-notes .claude/skills/release-notes $ npx degit Gord1y/countersign-skills/skills/thorough-diff-review .claude/skills/thorough-diff-review $ npx degit Gord1y/countersign-skills/skills/walkthrough .claude/skills/walkthrough $ npx degit Gord1y/countersign-skills/skills/writeups-cleanup .claude/skills/writeups-cleanup
$ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/Gord1y/countersign-skills/main/agents/builder.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/Gord1y/countersign-skills/main/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/Gord1y/countersign-skills/main/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/Gord1y/countersign-skills/main/agents/reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (16)
codebase-researchcontext-transferfeature-pr-descriptionhow-it-workshuman-voice-writingi18n-translateimpact-checkmemory-revieworchestratepr-review-triagepromotion-pr-descriptionqa-testerrelease-notesthorough-diff-reviewwalkthroughwriteups-cleanup
Subagents (4)
| builder model: sonnet | Implements one unit of an orchestrated run in its own git worktree, gated but never committed; the orchestrator lands and commits it. Spawned by the orchestrate skill with a pointer to the unit's brie |
| qa model: sonnet | QAs a finished change in the running product on every surface it touched, then writes the walkthrough; writes only evidence and notes into writeups/. Spawned by orchestrate after each landed batch tha |
| researcher model: haiku | Read-only code research for one factual question; reports at most 30 lines of paths, line ranges and facts. Spawned by codebase-research and by orchestrate's fact-gathering step. |
| reviewer model: sonnet | Read-only review of one orchestrated unit's worktree against its brief, with the thorough-diff-review checklist; reports at most 20 lines. Spawned by orchestrate for large units. |
Similar rigs
iuliandita/agents
Global prompts and subagent roles for coding agents, deployed to every harness you use.
Orchestrator 1.5k tok · · Q3
yourconscience/tackroom
Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, agent roles, and memory — synced natively to Claude Code, Codex, OMP/Pi, OpenCode, Droid, and Hermes. Commit-pinned and audited externals.
Orchestrator 1.4k tok · · Q8
Sagargupta16/foreman
Claude Code plugin: split a task into subtasks, route each to a predefined agent type on the cheapest model that fits, run them in dependency waves and verify once.
Orchestrator 2.3k tok · · Q0
Freakling/App-Director
Director-oriented AI coding workflow for small apps. You direct the design, AI builds it. Works for web, mobile, and desktop apps.
Fort Knox 2.3k tok · · Q41