resume-supervised-run

resume-supervised-run is a skill for Claude Code, Codex from SetraTheXX/Codex-Engineering-Workflow-Pack. It costs 62 tokens per session (610 once invoked), scanned A, original, MIT.

A recovery guide for supervised coding runs, which are monitored tasks with checkpoints, limits, and review information.

In plain words
What is it for?
It is for checking run status, budgets, ownership, verification results, blockers, and safe options such as resuming or cancelling.
Why use it?
It helps determine what completed safely, why work paused, and which recovery action is appropriate without losing trusted evidence.

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/resume-supervised-run
Any agent
npx skills add SetraTheXX/Codex-Engineering-Workflow-Pack --skill resume-supervised-run
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 resume-supervised-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/resume-supervised-run.svg)](https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/resume-supervised-run)
Your own site
<a href="https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/resume-supervised-run"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/resume-supervised-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 610 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 5.1 $0.00062 $0.00610
Opus 5 $0.00031 $0.00305
Sonnet 5 $0.00012 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 5d ago against content hash 78dbe8d0ca27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

resume-supervised-run 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 5d 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/resume-supervised-run/SKILL.md · 33 lines

What it actually says

Resume A Supervised Run

Read CEWP Core state before suggesting an action. This workflow may perform an explicitly requested non-model control, but it does not silently restart model work.

  1. If setup or capability readiness is in question, run cewp doctor --json and present actionable remediation.
  2. Run cewp supervise status [run-id] --json. Omitting the id selects the latest supervised run. This command regenerates progress.md from canonical state.
  3. Summarize:
    • run and checkpoint status;
    • plan revision and source identity;
    • completed evidence and attempts;
    • latest targeted/full verification and failure classification;
    • execution/worktree owner and backend;
    • consumed and remaining allocations, protected reserve, thresholds, and absolute ceiling;
    • managed usage as observed, estimated range with basis, and unavailable host usage as unknown;
    • pause reason, blocker, and exact next safe action.
  4. For paused-budget-safe, paused-budget-unverified, or paused-host-limit, explain the trusted checkpoint and any partial isolated work separately. Never infer that the host limit cleared.
  5. Apply a recovery control only with explicit user intent:
    • resume: cewp supervise resume <run-id> --yes --json;
    • add approved operations: cewp supervise add-budget <run-id> --operations <count> --allocation <implementation|repair|reviewer|finalization> --yes --json;
    • revise an unstarted checkpoint: cewp supervise revise <run-id> <changed fields> --json, then require fresh approval;
    • after a verified budget-safe pause, propose exactly one next bounded checkpoint with --goal, --scope, --verify, and --stop; CEWP seals prior evidence, and resume returns to fresh proposal approval;
    • rollback isolated work: cewp supervise rollback <run-id> --yes --json;
    • cancel or abandon: cewp supervise cancel <run-id> --yes --json or cewp supervise abandon <run-id> --yes --json;
    • record a blocker: cewp supervise block <run-id> --reason "<reason>" --json.
  6. After a non-model control, run status again and stop before the next model operation. Direct the user to the checkpoint workflow when they choose to execute, retry, or review.

Do not rewrite progress.md, delete evidence, claim hidden token/credit data, clear a host limit without explicit resume, mutate the source repo, or bypass policy, scope, verification, reviewer PASS, or finalization gates.

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. 5d ago First seen · 33 lines · 62 tokens per session scan A 78dbe8d0ca27

Subscribe to this mod's changes

resume-supervised-run is a skill published in the GitHub repository SetraTheXX/Codex-Engineering-Workflow-Pack (1 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 610 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-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

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-workflow-thinking

Sequential Thinking MCP for structured step-by-step analysis via --deepthink flag. Separate from UltraThink which is Claude's native extended reasoning mode. Use for multi-step analysis or architecture decisions.

modu-ai/moai-adk · 43 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