s0912758806p/agentic-sop-to-work
Plugin Claude Code
Loop Engineering for Claude Code agent loops — deterministic bounded termination (stall + budget), observable health, and bounded state. Ships agentic-sop-kit (human SOP → controlled loop) plus cross-domain review companions: Second Opinion (honesty reviewer), alcoa-guard (ALCOA+ data-integrity), plugin-forge (plugin…
s0912758806p/agentic-sop-to-work
Plugin Claude Code
Convert human SOPs into deterministic agentic workflows. Bundles the six-rung-ladder + agentic-sop + agentic-workflow-audit skills, the /sop-flow command, a project-scoped Stop-hook regression gate, and the portable agentic-sop-kit.
s0912758806p/agentic-sop-to-work
Command
Run the agentic-sop-kit workflow (extract→compute→report) and report the DRAFT result. Works out-of-the-box (bundled demo) even before a project adopts the kit.
s0912758806p/agentic-sop-to-work
Hook
Runs when a session starts on startup, executing session_check.py via python3. From s0912758806p/agentic-sop-to-work.
s0912758806p/agentic-sop-to-work
Hook
Runs when the agent finishes a response, executing stop_gate.py via python3. From s0912758806p/agentic-sop-to-work.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use to compute summary statistics (count/sum/mean/min/max) from a readings artifact, preserving the upstream source trace. Single tool. Reusable standalone.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use to extract numeric readings (key: value lines) from a plain-text input into a structured readings artifact with source-location trace. Single tool. Reusable standalone.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use to render a DRAFT Markdown summary report from a stats artifact, including a source-trace section; output is always a DRAFT for human review. Single tool. Reusable standalone.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
A method for turning a human standard operating procedure (SOP)—a documented step-by-step process—into a workflow an AI agent can follow and govern.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use when reviewing or auditing an existing agent / LLM-pipeline architecture — e.g. 'is my workflow actually decomposed or secretly a mega-agent?', 'are my task boundaries and success criteria right?' — even without the word 'audit'. ｜ 要檢視／review／稽核既有 agent 或 LLM pipeline 的架構，或問「有沒有拆好」「是不是變成 mega agent」「task…
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
A decision checklist for deciding whether new code, a dependency, an abstraction, or a module is actually needed. It moves from the simplest option to a minimal working solution.
s0912758806p/agentic-sop-to-work
Plugin Claude Code
Deterministic ALCOA+ data-integrity linter for a record/dataset: checks Attributable / Contemporaneous / Complete / Accurate / Consistent in code, and surfaces the human-judgment slice (authorization, gap justification) as a 【待補】 checklist it never auto-concludes. DEGRADED mode lints any CSV/JSON record against a…
s0912758806p/agentic-sop-to-work
Command
Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency). Deterministic findings + a human-judgment checklist; the report is a DRAFT, the human owns the verdict.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use when checking a record / dataset / GMP document for ALCOA+ data integrity — attribution, contemporaneity (backdating), completeness, accuracy (recompute / in-spec), consistency — before a human approves. DEGRADED mode lints any CSV/JSON record against a declared .alcoa.json contract; FULL mode snaps onto an…
s0912758806p/agentic-sop-to-work
Plugin Claude Code
Claude Code plugin linter + scaffolder. lint validates a plugin (or a whole marketplace) against a house grammar — a strict superset of the usual manifest/frontmatter checks plus stdlib-only, hook-protocol, and test-harness invariants; scaffold generates a grammar-conformant plugin skeleton that passes the linter b.
s0912758806p/agentic-sop-to-work
Command
Lint a Claude Code plugin / marketplace against house invariants, or scaffold a new grammar-conformant plugin skeleton.
s0912758806p/agentic-sop-to-work
Plugin Claude Code
bad-plugin. Turn human SOPs into deterministic, gated agentic workflows — a Claude Code plugin.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Turn human SOPs into deterministic, gated agentic workflows — a Claude Code plugin.
s0912758806p/agentic-sop-to-work
Plugin Claude Code
good-plugin. Turn human SOPs into deterministic, gated agentic workflows — a Claude Code plugin.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
demo good plugin.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use when creating, scaffolding, or linting a Claude Code plugin — generate a grammar-conformant plugin skeleton, or validate a plugin / whole marketplace against house invariants (manifest, frontmatter, stdlib-only, hook protocol, test harness). ｜ 要新建 / scaffold 一個 Claude Code plugin，或 lint 既有 plugin / 整個 marketplace…
s0912758806p/agentic-sop-to-work
Plugin Claude Code
Independent adversarial honesty reviewer for a DRAFT output: checks claims-vs-evidence (no fabrication, no overreach, no invented IDs) before a human approves. FULL mode reads an agentic-sop-kit run dir's trace; DEGRADED mode reviews any plain document with user-supplied inputs. Deterministic honesty checks in code +…
s0912758806p/agentic-sop-to-work
Command
Get an independent adversarial SECOND OPINION on a finished DRAFT — check its claims against its evidence (no fabrication, no overreach) before a human approves. FULL mode reads an agentic-sop-kit run dir's trace; DEGRADED mode reviews any document with supplied inputs.
s0912758806p/agentic-sop-to-work
Skill Claude CodeCodex
Use when asked to get a second opinion on a finished DRAFT, fact-check or double-check a report's claims against its evidence, sanity-check before sign-off, or red-team an output for fabrication / overreach / invented IDs — even without the word "honesty". Works on an agentic-sop-kit run dir (FULL, uses the run's…