AI Agent Workflow Collection

Scaffolds a standalone Bash 4.0+ script — a single-file CLI tool, glue automation, or ops utility — with explicit shebang, set -euo pipefail, header comment, readonly constants, die helper, local variables, main function, and a sourceable guard. Use when the user wants to "scaffold a bash script", "create a bash script", or "scaffold a shell script". Not for POSIX sh portability targets, Claude Code hooks, or scripts that would be cleaner in Python — route to the appropriate primitive.

Scaffolds a GitHub Actions workflow — a YAML file under .github/workflows/ — with top-level least-priv permissions:, SHA-pinned uses:, per-job timeout-minutes, workflow-level defaults.run.shell: bash, scoped triggers, harden-runner as first step, set -euo pipefail in every multi-line run:, and deliberate concurrency posture (cancel-in-progress for PR/push, no-cancel for deploy). Use when the user wants to "scaffold a ci workflow", "create a github workflow", or "build a github actions workflow for X". Not for composite actions (action.yml — separate primitive), org rulesets, Dependabot configs, or GitHub Apps.

Use when the user wants to "scaffold a help skill", "add a / :help command", or "build a plugin index skill", or wants to give a plugin an orientation surface that lists its skills and common workflows. Produces a SKILL.md at plugins/ /skills/help/SKILL.md.

Builds a Claude Code hook (event-driven quality gate) with a script and the corresponding settings.json hooks entry. Use when the user wants to "create a hook", "add a PostToolUse hook", or "enforce quality on tool use".

Scaffolds a top-level Makefile for repository workflow orchestration — strict-shell header, safety MAKEFLAGS, .PHONY coverage, self-documenting help from description comments, overridable ?= config, and a flat target graph with scoped clean. Use when the user wants to "create a makefile", "scaffold a makefile", or "new makefile for [X]". Not for POSIX-make, compilation-driving Makefiles, or multi-module recursive builds.

Scaffolds a reproducible pre-commit configuration — a .pre-commit-config.yaml at the repo root (optionally with local shell scripts under scripts/hooks/) that runs formatters, linters, and validators against staged changes via the pre-commit framework. Pins every rev:, declares scope per hook, serializes file-mutators, and documents the bootstrap. Use when the user wants to "set up pre-commit", "scaffold pre-commit hooks", or "configure .pre-commit-config.yaml". Not for hand-rolled .git/hooks/ scripts, not for pre-push / commit-msg / server-side hooks, not for CI pipelines — route to the appropriate primitive.

Scaffolds a standalone Python 3 script — a single-file CLI tool, automation helper, or data-wrangling utility — with shebang, module docstring, main(argv) -> int, main guard via sys.exit(main()), argparse parser, KeyboardInterrupt handling, and declared dependencies. Use when the user wants to "scaffold a python script", "create a python script", or "build an automation script in python". Not for long-running services, packages with multiple modules, or Claude Code hooks — route to the appropriate primitive instead.

Scaffolds a project's top-level README.md — the README.md at a repository root that orients a first-time reader in the top 30 seconds. Produces a conditionalized template with a single H1, one-sentence description, problem statement, badges block, H2 section sequence (Prerequisites → Installation → Usage → Configuration → Troubleshooting → Contributing → License), fenced code blocks with language tags, and placeholder discipline. Use when the user wants to "scaffold a README", "create a README", or "bootstrap README.md". Not for sub-package READMEs inside a monorepo, docs-site landing pages, or GitHub org-profile READMEs — those have different audiences and out of scope.

Scaffold a root-level RESOLVER.md — a dual routing table (filing for writes, context for reads) plus an AGENTS.md pointer and a trigger-eval sidecar at .resolver/evals.yml. Use when the user wants to "scaffold RESOLVER.md", "create a resolver", or "add a routing table for filing and context".

Create a Claude Code rule under .claude/rules/ — a markdown instruction file with optional paths: frontmatter for path-scoping. Use when the user wants to "create a rule", "capture this convention", or "enforce this pattern".

Scaffolds a primitive-pair — a matched build- and check- skill sharing a single distilled principles doc under shared/references/, plus one references/check- .md per judgment dimension on the check half. Distills best-practice material (files, URLs, pasted text, or the model's own domain knowledge) into one rubric that both halves reference. Use when the user wants to "create a skill pair", "scaffold build and check skills for X", or "codify best practices for a new primitive". Not for creating a single skill — route to /build:build-skill. Not for auditing an existing pair — route to /build:check-skill on each half.

Scaffolds a Claude Code custom subagent definition — a .md file under .claude/agents/ with a routing-oriented description, an explicit tools allowlist sized to the workflow, a bounded system prompt in the markdown body, and explicit failure behavior. Use when the user wants to "create a subagent", "scaffold an agent", or "make a custom agent". Not for skills (route to /build:build-skill), hooks (route to /build:build-hook), or rules (route to /build:build-rule).

Audits a Bash 4.0+ script against 34 deterministic rules emitted as JSON envelopes (shebang, set -euo pipefail, header comment, main + sourceable guard, readonly constants, mktemp+trap pairing, shellcheck rule set SC2086 / SC2046 / SC2068 / SC2154 / SC2155 / SC2006 / SC2010 / SC2012 / SC2045 / SC2013 / SC2162 / SC2038 / SC2164 / SC2002 / SC2294, shfmt format compliance, eval / GNU-flag / /tmp/ literal flagging, secret patterns, line count, naming conventions, command preflight) plus six judgment dimensions (output discipline, input validation, performance intent, function design, commenting intent, cross-entity collision). Use when the user wants to "audit a bash script", "lint a bash script", or "run shellcheck on this". Not for POSIX sh portability — refused at scope. Not for Python scripts — route to /build:check-python-script.

Audits a GitHub Actions workflow YAML file (or a directory under .github/workflows/) against 30 deterministic checks (top-level name:, permissions, timeouts, concurrency, SHA-pinning for every uses:, no @main/@master/floating refs, pullrequesttarget + PR checkout combo, template injection in run:, deprecated commands, secrets-in-top-env, fork-PR secret exposure, harden-runner first, persist-credentials, strict bash, actionlint, zizmor, yamllint, shellcheck on extracted run: content) plus seven judgment dimensions. Use when the user wants to "audit a github workflow", "lint my workflow", or "run zizmor on this". Not for composite actions — different rubric.

Use when the user wants to "audit a help skill", "review my plugin index", or "verify my help-skill is up to date". Audits a plugins/ /skills/help/SKILL.md against the help-skill rubric — coverage, freshness, frontmatter fidelity, plus five judgment dimensions and a trigger-collision check.

Audits Claude Code hooks configuration for event coverage, script safety, async and blocking contradictions, Stop hook loop risks, rule overlap, and idempotency. Use when the user wants to "audit hooks", "review hooks", or "are my hooks safe".

Audits a top-level Makefile against 29 deterministic checks (strict-shell pin, .SHELLFLAGS, MAKEFLAGS warnings, .PHONY coverage, tab-indent, header comment, help-target patterns, variable-assignment discipline, top-level shell, destructive-op guards including rm -rf/sudo/global-install/curl-pipe, recipe hygiene, secrets, file/line size, optional checkmake wrap) plus seven judgment dimensions and a Tier-3 cross-Makefile collision check. Use when the user wants to "audit a makefile", "lint a makefile", or "review this makefile". Not for POSIX-make, compilation trees, or recursive multi-module builds — different rubric.

Audits a .pre-commit-config.yaml (and referenced local hook scripts) against 20 deterministic checks (YAML shape, rev: pinning, scope declarations, network-call / destructive-command / error-suppression patterns, shell-script strict mode, hook explicit-name and require-serial hygiene) plus seven judgment dimensions and a Tier-3 cross-config collision check. Use when the user wants to "audit pre-commit", "lint pre-commit", or "review my pre-commit hooks". Not for hand-rolled .git/hooks/ — out of scope. Not for CI pipelines — route elsewhere.

Audits a standalone Python 3 script against 25 deterministic checks (shebang, main guard, argparse shape, declared dependencies, ruff-backed AST lints, line count, secret patterns) plus nine judgment dimensions (output discipline, input validation, dependency posture, performance intent, naming, function design, module-scope discipline, literal intent, commenting intent) and a Tier-3 cross-script collision check. Use when the user wants to "audit a python script", "lint a python script", or "review this script". Not for general-purpose shell scripts — route to /build:check-bash-script.

Audit a root-level resolver — verify AGENTS.md pointer, managed-region integrity, filing-table coverage against disk, context-table actionability, and trigger-eval pass rate. Use when the user wants to "audit a resolver", "validate routing table", or "find dark capabilities".

Check a Claude Code rule library under .claude/rules/ for path-glob validity, vague phrasing, contradictions, and oversize files. Use when the user wants to "audit rules", "review my rules", or "find conflicting rules".

Design a skill-chain from a goal, or check an existing skill-chain manifest for structural and contract issues. Use when the user wants to "design a skill-chain", "audit a chain", or "repair a chain".

Audits pair-level integrity of a primitive-pair (the artifact /build:build-skill-pair produces) by walking the four required artifact slots — principles doc, build- /SKILL.md, check- /SKILL.md, and the primitive-routing.md registration — and reports cross-artifact issues a per-SKILL.md checker cannot see: missing principles doc, divergent principles paths between halves, absent routing registration, missing build→check handoff. Per-half structural compliance with the unified pattern (check-skill-pattern.md) is delegated to plugins/build/shared/scripts/checkskillpattern.py. Use when the user wants to "audit a skill pair", "review a primitive pair", or "validate the skill pair for X". Not for auditing a single SKILL.md — route to /build:check-skill. Not for re-distilling a stale principles doc — route to /build:build-skill-pair.

Audits Claude Code custom subagent definitions against deterministic Tier-1 checks (location, frontmatter shape, naming, tools hygiene, prompt size, body structure, secret patterns) and seven judgment dimensions (scope discipline, routing-description quality, tool proportionality, output contract, voice & framing, failure behavior, injection surface). Use when the user wants to "audit a subagent", "review agent permissions", or "validate a subagent definition". Not for skills (route to /build:check-skill), hooks (route to /build:check-hook), or rules (route to /build:check-rule).