Scripts for agents, shared between my repositories.
6,612
stars
614
commits
Shell
primary language
Sep 8, 2026
updated
Shared agent instructions, skills, and small portable helpers for Peter's local workspaces.
This repo is the canonical place for:
AGENTS.MD: shared hard rules for Codex/Claude-style agentsskills/: reusable workflow skills, including repo-owned skills exposed by symlinkscripts/: dependency-light helpers used across projectshooks/: local guardrails such as skill validationSkills are the main routing layer. Each skills/<name>/SKILL.md has YAML front matter:
---
name: skill-name
description: "Short generic trigger phrase."
---
Rules:
skills/<name>/scripts/ when a workflow has repeatable commands.scripts/validate-skills.description in front matter.Global discovery is built by scripts/sync-skills (idempotent; run on every Mac after cloning or adding skills):
~/.codex/skills/agent-scripts -> ~/Projects/agent-scripts/skills, ~/.codex/skills/manager -> ~/Projects/manager/skills.~/.claude/skills/<name>/SKILL.md (exactly one level deep; per-entry symlinks are followed, category subfolders are not scanned — verified on 2.1.197). It gets a flat per-skill link mirror covering both repos plus machine-local ~/.codex/skills/<name> extras.Shared personal skills live as real folders in skills/. Public OpenClaw shared skills live in ../agent-skills and are exposed here with tracked relative symlinks. Repo-owned skills stay canonical in their repo and are exposed here the same way, for example:
skills/autoreview -> ../../agent-skills/skills/autoreview
skills/discrawl -> ../../discrawl/.agents/skills/discrawl
Current symlinked repo-owned skills include birdclaw, discrawl, gog, imsg, slacrawl, wacli, and wacrawl.
Shared hard rules live in AGENTS.MD.
Global setup (also maintained by scripts/sync-skills; Claude Code reads CLAUDE.md only, so it links to the shared AGENTS.MD):
~/.codex/AGENTS.md -> ~/Projects/agent-scripts/AGENTS.MD~/.claude/CLAUDE.md -> ~/Projects/agent-scripts/AGENTS.MD~/.claude/AGENTS.md -> ~/Projects/agent-scripts/AGENTS.MDDownstream repos should use a pointer-style AGENTS.MD:
READ ~/Projects/agent-scripts/AGENTS.MD BEFORE ANYTHING (skip if missing).
Repo-specific rules go below that pointer. Do not copy the shared blocks into downstream repos.
scripts/sync-skills
AGENTS.MD pointers.scripts/validate-skills
skills/*/SKILL.md.name and description.git config core.hooksPath hooks.scripts/docs-list.ts
docs/.summary and read_when front matter.scripts/browser-tools.ts
start --profile, nav <url>, eval '<js>', screenshot, console, network, search --content "<query>", content <url>, inspect, kill --all --force.bun build scripts/browser-tools.ts --compile --target bun --outfile bin/browser-tools.Treat this repo as canonical for shared agent rules and portable helper scripts.
When syncing downstream repos:
AGENTS.MD.For submodules, repeat the pointer check inside each subrepo, push those changes, then bump submodule SHAs in the parent repo.
Shell
44.7%
TypeScript
26.6%
JavaScript
13.3%
Python
10.9%
Ruby
4.1%
Scripts for agents, shared between my repositories.
6,612
stars
614
commits
Shell
primary language
Sep 8, 2026
updated
Shared agent instructions, skills, and small portable helpers for Peter's local workspaces.
This repo is the canonical place for:
AGENTS.MD: shared hard rules for Codex/Claude-style agentsskills/: reusable workflow skills, including repo-owned skills exposed by symlinkscripts/: dependency-light helpers used across projectshooks/: local guardrails such as skill validationSkills are the main routing layer. Each skills/<name>/SKILL.md has YAML front matter:
---
name: skill-name
description: "Short generic trigger phrase."
---
Rules:
skills/<name>/scripts/ when a workflow has repeatable commands.scripts/validate-skills.description in front matter.Global discovery is built by scripts/sync-skills (idempotent; run on every Mac after cloning or adding skills):
~/.codex/skills/agent-scripts -> ~/Projects/agent-scripts/skills, ~/.codex/skills/manager -> ~/Projects/manager/skills.~/.claude/skills/<name>/SKILL.md (exactly one level deep; per-entry symlinks are followed, category subfolders are not scanned — verified on 2.1.197). It gets a flat per-skill link mirror covering both repos plus machine-local ~/.codex/skills/<name> extras.Shared personal skills live as real folders in skills/. Public OpenClaw shared skills live in ../agent-skills and are exposed here with tracked relative symlinks. Repo-owned skills stay canonical in their repo and are exposed here the same way, for example:
skills/autoreview -> ../../agent-skills/skills/autoreview
skills/discrawl -> ../../discrawl/.agents/skills/discrawl
Current symlinked repo-owned skills include birdclaw, discrawl, gog, imsg, slacrawl, wacli, and wacrawl.
Shared hard rules live in AGENTS.MD.
Global setup (also maintained by scripts/sync-skills; Claude Code reads CLAUDE.md only, so it links to the shared AGENTS.MD):
~/.codex/AGENTS.md -> ~/Projects/agent-scripts/AGENTS.MD~/.claude/CLAUDE.md -> ~/Projects/agent-scripts/AGENTS.MD~/.claude/AGENTS.md -> ~/Projects/agent-scripts/AGENTS.MDDownstream repos should use a pointer-style AGENTS.MD:
READ ~/Projects/agent-scripts/AGENTS.MD BEFORE ANYTHING (skip if missing).
Repo-specific rules go below that pointer. Do not copy the shared blocks into downstream repos.
scripts/sync-skills
AGENTS.MD pointers.scripts/validate-skills
skills/*/SKILL.md.name and description.git config core.hooksPath hooks.scripts/docs-list.ts
docs/.summary and read_when front matter.scripts/browser-tools.ts
start --profile, nav <url>, eval '<js>', screenshot, console, network, search --content "<query>", content <url>, inspect, kill --all --force.bun build scripts/browser-tools.ts --compile --target bun --outfile bin/browser-tools.Treat this repo as canonical for shared agent rules and portable helper scripts.
When syncing downstream repos:
AGENTS.MD.For submodules, repeat the pointer check inside each subrepo, push those changes, then bump submodule SHAs in the parent repo.
Shell
44.7%
TypeScript
26.6%
JavaScript
13.3%
Python
10.9%
Ruby
4.1%