specrew: Skill for Claude Code

.squad/skills/resume-state-repair/SKILL.md

resume-state-repair is a skill for Claude Code, Codex from alonf/specrew. It costs 24 tokens per session (500 once invoked), scanned A, original, MIT.

A recovery method for correcting stale execution information by comparing it with the authoritative task table before work resumes.

In plain words
What is it for?
Use it to rebuild the remaining-task list, restore the active task, and repair resume metadata before continuing execution.
Why use it?
It prevents an interrupted workflow from skipping unfinished tasks because its saved state is out of date.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is alonf/specrew's own configuration. It tells Claude Code and Codex how to work on specrew itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything specrew configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alonf/specrew. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alonf/specrew/main/.squad/skills/resume-state-repair/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alonf/specrew

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-state-repair

README.md
[![agentmods](https://agentmods.dev/badge/skills/alonf/specrew/resume-state-repair/github.svg)](https://agentmods.dev/skills/alonf/specrew/resume-state-repair)
Your own site
<a href="https://agentmods.dev/skills/alonf/specrew/resume-state-repair"><img src="https://agentmods.dev/badge/skills/alonf/specrew/resume-state-repair/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for resume-state-repair

Your own site · 80×15
<a href="https://agentmods.dev/skills/alonf/specrew/resume-state-repair"><img src="https://agentmods.dev/badge/skills/alonf/specrew/resume-state-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00024 $0.00500
Opus 5 $0.00012 $0.00250
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 7d ago against content hash 95e6f564d4d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

resume-state-repair 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 7d 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.

.squad/skills/resume-state-repair/SKILL.md · 41 lines

What it actually says

Context

Use this when a resume or recovery helper reads both state.md and plan.md, and stale execution metadata could cause the workflow to skip incomplete tasks after an interruption.

Patterns

  • Treat the task table in plan.md as the authority for which tasks are still planned, in-progress, needs-rework, blocked, or done.
  • Let state.md carry only the volatile execution details that may be newer than the plan table, especially active in-progress tasks.
  • Rebuild Tasks Remaining from authoritative planned tasks instead of trusting a stale comma-separated list.
  • Preserve or infer In Progress from state.md first, then fall back to task-table statuses when state metadata is missing.
  • Rewrite repaired metadata before appending or refreshing any managed resume report so the artifact itself becomes the recovery output.

Examples

  • state.md says Tasks Remaining: T-003, but plan.md still shows T-002 and T-003 as planned. Repair Tasks Remaining, set T-002 in progress on continue, and keep T-003 queued.
  • state.md is missing In Progress and Updated. Reconstruct them from the task table and write the repaired fields during resume.

Anti-Patterns

  • Trusting a stale Tasks Remaining list over the live task table.
  • Leaving repaired resume results only in JSON output while state.md stays stale.
  • Using task-table order alone as the execution order when the iteration can complete tasks out of order.
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. 7d ago First seen · 41 lines · 24 tokens per session scan A 95e6f564d4d7

Subscribe to this mod's changes

resume-state-repair is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 500 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories