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 jschulte/claude-plugins --skill editor-rescuegit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/editor-rescue)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/editor-rescue"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/editor-rescue/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.
<a href="https://agentmods.dev/skills/jschulte/claude-plugins/editor-rescue"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/editor-rescue.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00127 | $0.01062 |
| Opus 5.5 | $0.00051 | $0.00425 |
| Sonnet 5.5 | $0.00025 | $0.00212 |
| Haiku 4.5 | $0.00013 | $0.00106 |
Grade A, and why
editor-rescue 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 27d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
editor-rescue
Editors with hot exit keep every unsaved buffer forever. This skill backs up that state, triages each unique buffer into keep, maybe or toss, writes organized notes, and then moves the state aside so the editor opens empty. Nothing is ever deleted.
Scripts are in this skill's scripts/ directory and need only the Python 3
standard library. OUT defaults to ~/editor-rescue-<date>.
Procedure
- Have the user fully quit each editor (Cmd-Q, not just closing windows).
A running Sublime keeps rewriting its session, and
reset.pyrefuses to run while an editor is open. - Extract:
python3 <skill-dir>/scripts/extract.py [--out DIR]. This copies each editor's state intoOUT/_backup/, dumps unique buffers toOUT/_work/raw/, auto-tosses empty buffers and terminal or test output, and writes triage batches toOUT/_work/batches/. - Triage: start one background subagent per batch, all in a single
message, on a cheaper model (e.g. sonnet). Give each the prompt in
references/triage-prompt.md, with{LIST}set toOUT/_work/batches/batch_NN.listand{RESULT}set toOUT/_work/results/batch_NN.json. If there is only one small batch (about 20 files or fewer), triage it yourself with the same prompt. - Assemble:
python3 <skill-dir>/scripts/assemble.py OUT. If it printsUNREVIEWEDpaths, read those files yourself (usually tiny fragments), writeOUT/_work/results/manual.jsonin the same schema, and run assemble again until nothing is left unreviewed. - Spot-check: read
OUT/README.md, plus a few files fromkeep/and entries inTOSSED.md. - Report: give the user the counts, the highlights, how many buffers held
credentials, and the
DIRTY-FILES.mdentries whose only copy is the buffer. Tell them the raw secrets are still inOUT/_work/raw/andOUT/_backup/, soOUTstays private and gets deleted once they have rotated the keys. - Reset, only after the user says yes to the report. The original "close
it all" request does not count as that yes. Run
python3 <skill-dir>/scripts/reset.py OUTas a dry run and show its output. Then run it again with--yes. It moves Sublime sessions and VS Code-familyBackups/intoOUT/_backup/<editor>/moved-aside/, and clears the reopen-window list. Without that last step, VS Code reopens every empty window. - Suggest turning hot exit off so this doesn't happen again: Sublime
"hot_exit": "disabled", VS Code"files.hotExit": "off".
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago First seen · 79 lines · 127 tokens per session scan A fc969b7624ed
editor-rescue is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 127 tokens to every session and 1,062 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
Profile
View, edit, or clear the LifeOS User Model (PRINCIPALIDENTITY.md) — persistent identity context loaded at session startup. Three intents: View, Edit (identity, goals, constraints, preferences), Clear (reset). Read by Algorithm OBSERVE and skills for personalization. USE WHEN profile, show profile, view profile, who am…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
daily-briefing
Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…