recover

recover is a skill for Claude Code from moonxorsun/focus-claude-code. It costs 23 tokens per session (622 once invoked), scanned A, original, MIT.

A context-recovery skill for restoring work from an earlier session when automatic restoration fails or is incomplete.

In plain words
What is it for?
Resuming interrupted work, reviewing recovered context, completing an old session, or restarting the focus process.
Why use it?
It helps recover previous task information after an interruption or failed session restore.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Part of the focus plugin — 4 skills, 4 commands, 5 hooks shipped together

Good fit Resuming interrupted work, reviewing recovered context, completing an old session, or restarting the focus process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moonxorsun/focus-claude-code/recover
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.

Any agent
npx skills add moonxorsun/focus-claude-code --skill recover
Clone the repo
git clone --depth 1 https://github.com/moonxorsun/focus-claude-code

Made for: Claude Code.

Or install focus, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 5 hooks.

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 recover

README.md
[![agentmods](https://agentmods.dev/badge/skills/moonxorsun/focus-claude-code/recover.svg)](https://agentmods.dev/skills/moonxorsun/focus-claude-code/recover)
Your own site
<a href="https://agentmods.dev/skills/moonxorsun/focus-claude-code/recover"><img src="https://agentmods.dev/badge/skills/moonxorsun/focus-claude-code/recover.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 622 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.
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 $0.00023 $0.00622
Opus 5 $0.00012 $0.00311
Sonnet 5 $0.00005 $0.00124
Haiku 4.5 $0.00002 $0.00062

Measured 7d ago against content hash c6c69dd36cf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

recover 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.

plugins/focus/skills/recover/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment

Variable Default
CLAUDE_FOCUS_DIR .claude/tmp/focus

Use $CLAUDE_FOCUS_DIR in paths. If unset, use the default .claude/tmp/focus.

Context Recovery

Recover context from previous sessions when Claude's automatic session restore fails or is incomplete.

CRITICAL: Follow Script Output Exactly

This skill uses a script-driven flow. You MUST:

  1. Run the script
  2. Read the [REQUIRED] directive in the output
  3. Execute exactly what the directive says (usually AskUserQuestion)
  4. Based on user's choice, run the next script or skill

DO NOT improvise, skip steps, or ask different questions than specified.

Flow

Step 1: Run Recovery Script

python "{{FOCUS_PLUGIN_ROOT}}/scripts/recover_context.py"

Step 2: Follow the [REQUIRED] Directive

The script output ends with a [REQUIRED] block. Execute it exactly.

Scenario A: focus_context.md EXISTS

Script outputs dual-source recovery + directive to ask:

  • Continue task → Start working from Current Phase
  • Complete session → Run /focus:done
  • Restart → Delete context, run /focus:start
  • Cancel → Do nothing, end skill
Scenario B: focus_context.md NOT EXISTS

Script outputs session list + directive to ask:

  • Recover history → Proceed to Step 3
  • Start new → Run /focus:start
  • Cancel → Do nothing, end skill

Step 3: (If user chose "Recover history")

Follow the [REQUIRED] Step 2 directive from script output exactly.

The script provides pre-formatted options (max 4):

  • Sessions 1-3 (or 1-4 if total ≤ 4)
  • "More..." option if > 4 sessions (user enters number in "Other")

DO NOT filter or modify the options - the script handles smart filtering:

  • startup/clear sessions: current session excluded
  • resume/compact sessions: current session included

After user selects, run:

python "{{FOCUS_PLUGIN_ROOT}}/scripts/recover_context.py" --recover <N>

After recovery, inform user they can run /focus:start to create a new focus session.

Read the full file on GitHub · 86 lines

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 · 86 lines · 23 tokens per session scan A c6c69dd36cf7

Subscribe to this mod's changes

recover is a skill published in the GitHub repository moonxorsun/focus-claude-code (5 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 622 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens