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.
npx skills add moonxorsun/focus-claude-code --skill recovergit clone --depth 1 https://github.com/moonxorsun/focus-claude-codeWrote 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.
[](https://agentmods.dev/skills/moonxorsun/focus-claude-code/recover)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Run the script
- Read the
[REQUIRED]directive in the output - Execute exactly what the directive says (usually AskUserQuestion)
- 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/clearsessions: current session excludedresume/compactsessions: 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.
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.
- 7d ago First seen · 86 lines · 23 tokens per session scan A c6c69dd36cf7
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.
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.
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.…
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…
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.
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…
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.