run-supervised-checkpoint

run-supervised-checkpoint is a skill for Claude Code, Codex from SetraTheXX/Codex-Engineering-Workflow-Pack. It costs 50 tokens per session (755 once invoked), scanned A, original, MIT.

A workflow for running an already proposed supervised checkpoint in the CEWP engineering process. CEWP is a system that controls child workspaces, approvals, model operations, verification, and review.

In plain words
What is it for?
Use it to inspect checkpoint status, approve and execute approved work, run local verification, review evidence, preview changes, or finalize a checkpoint.
Why use it?
It keeps execution tied to the recorded plan and required approvals instead of treating a proposed checkpoint as automatically ready to run.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/setrathexx/codex-engineering-workflow-pack/run-supervised-checkpoint
Any agent
npx skills add SetraTheXX/Codex-Engineering-Workflow-Pack --skill run-supervised-checkpoint
Clone the repo
git clone --depth 1 https://github.com/SetraTheXX/Codex-Engineering-Workflow-Pack

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for run-supervised-checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/run-supervised-checkpoint.svg)](https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/run-supervised-checkpoint)
Your own site
<a href="https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/run-supervised-checkpoint"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/run-supervised-checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00755
Opus 5 $0.00025 $0.00378
Sonnet 5 $0.00010 $0.00151
Haiku 4.5 $0.00005 $0.00076

Measured 4d ago against content hash eeea4172c053, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-supervised-checkpoint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cewp/skills/run-supervised-checkpoint/SKILL.md · 24 lines

What it actually says

Run A Supervised Checkpoint

Use canonical JSON from cewp supervise; generated Markdown is a view, not mutable state. Keep the ChatGPT/Codex host in the operator role while CEWP owns the isolated child worktree.

  1. Run cewp supervise status [run-id] --json and state the current run/checkpoint status, plan revision, owner/backend, latest evidence, budget consumption, warnings, blocker, and next safe action.
  2. Perform no more than one CEWP-controlled model operation per invocation. Local verification commands do not count as model operations, but their approved limits still apply.
  3. Follow only the transition matching canonical state:
    • proposed: show the plan and run cewp supervise approve <run-id> --yes --json only after explicit approval. Stop before dispatch.
    • approved/ready: if the operator explicitly requested a Codex task class, model, or effort, record it first with cewp supervise effort <run-id> --operation implementation --task-class <class> [--model <model>] [--effort <effort>] --yes --json. Never infer model or effort from the class. Then run cewp supervise execute <run-id> --yes --json only after explicit execution approval. If dispatch reaches verifying, run cewp supervise verify <run-id> --json; then stop at the verified, repair, paused, or blocked result.
    • needs-repair/repair-ready: explain the failure signature and remaining repair allocation. Record any explicitly requested repair-specific Codex selection through cewp supervise effort ... --operation repair ... --yes --json; do not reuse or change implementation settings implicitly. Run cewp supervise retry <run-id> --yes --json only when the user explicitly chooses retry, then run local verification and stop.
    • checkpoint-complete/verified: offer final review or a safe pause for one manually bounded next checkpoint. For final review, record any explicitly requested independent-review Codex selection through cewp supervise effort ... --operation reviewer ... --yes --json, record cewp supervise continue <run-id> --json, run cewp supervise review <run-id> --yes --json, and stop at the reviewer decision. For more work, hand off to the resume workflow without dispatching another model operation.
    • review-passed: run cewp supervise receipt <run-id> --json to preview the receipt. Do not finalize in the same step unless the user already gave explicit finalize intent after seeing equivalent receipt facts.
    • ready-to-finalize: run cewp supervise finalize <run-id> --yes --json only after explicit finalization approval.
    • any paused-* or blocked: do not dispatch. Present Core recovery actions and hand off to the resume workflow.
  4. Treat any nonzero command, scope warning, failed verification, missing reviewer decision, REQUEST_CHANGES, BLOCK, exhausted allocation, host limit, or ownership mismatch as a closed gate.
  5. Report the resulting canonical status and exact next safe command. Never label dispatch completion, partial files, or a reviewer request as checkpoint success.

Do not edit the managed worktree from the host task, bypass --yes, borrow protected allocations, automatically add budget, switch backend/provider, merge, push, publish, tag, or release.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 24 lines · 50 tokens per session scan A eeea4172c053

Subscribe to this mod's changes

run-supervised-checkpoint is a skill published in the GitHub repository SetraTheXX/Codex-Engineering-Workflow-Pack (1 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 755 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

hns-lsel-curator

Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…

modu-ai/moai-adk · 135 tokens

hns-workflow-ci-loop

Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…

modu-ai/moai-adk · 76 tokens

moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…

modu-ai/moai-adk · 76 tokens

moai-harness-learner

Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.

modu-ai/moai-adk · 61 tokens

hns-oss-docs-readme-sync

README 4-file synchronization procedure for the oss-docs harness: Korean README.ko.md as primary source, en/ja/zh derivation, the shared language-switcher header contract, section-order parity checklist, and the manual verification recipe (no linter exists for READMEs). Loaded by the content-author and…

modu-ai/moai-adk · 83 tokens

moai-domain-humanize

AI text humanization and 윤문 (post-editing) specialist that detects and removes AI tells while preserving meaning, facts, and figures. Covers Korean, English, Japanese, and Chinese with a shared severity model (S1/S2/S3), quality grades (A/B/C/D), and 30%/50% over-editing guardrails. Use to make AI-generated text read…

modu-ai/moai-adk · 101 tokens