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 fledgeling-co/fledgeling-plugins --skill recover-claude-codegit clone --depth 1 https://github.com/fledgeling-co/fledgeling-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/fledgeling-co/fledgeling-plugins/recover-claude-code)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/recover-claude-code"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/recover-claude-code/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/fledgeling-co/fledgeling-plugins/recover-claude-code"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/recover-claude-code.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 | $0.00239 | $0.03897 |
| Opus 5.5 | $0.00096 | $0.01559 |
| Sonnet 5.5 | $0.00048 | $0.00779 |
| Haiku 4.5 | $0.00024 | $0.00390 |
Grade A, and why
recover-claude-code 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 1mo 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recovering Claude Code after a crash
When a terminal process dies, the sessions inside it stop mid-sentence. Their transcripts, their workflow journals and their subagents' accumulated context all survive on disk — the work is not lost, it is unattached. This skill reattaches it.
The failure worth designing against is not losing the work. It is recovering it badly: starting a replacement agent on the same prompt with none of its predecessor's context, so it re-reads the same files, re-derives the same findings, and sometimes re-does work that is already committed. A recovery that cold-starts looks like it worked and quietly costs an hour.
Deliver what was asked, at the scope intended: recover the sessions that are actually dead and the work they were actually owed. Resist widening into fixing the underlying work.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It turns this skill's prohibitions — never resume a live session, never --fork-session, never edit the original journal — into a bound ledger with a readback command per row, and gives §4's 'every agent that was in flight' a denominator. Other models skip it.
1. See what is there
python3 scripts/scan_crashed.py --minutes 60 # the default window
python3 scripts/scan_crashed.py --minutes 180 --json # for the tab driver
python3 scripts/scan_crashed.py --project perch # one project
Read-only. It reports, per session: whether it is live, its working directory, its peer
name, whether it was cut mid-turn, and for each workflow run how many agent() calls
returned against how many started, which agents were mid-tool, and where the run's script
is on disk.
It separates three states, and only one of them is yours to touch:
| State | What it means | What to do |
|---|---|---|
LIVE, attached to a tty |
in ~/.claude/sessions/ under a running pid, in a terminal tab |
nothing — see §3 |
LIVE, no tty |
outlived the terminal that owned it | stop it first — see §2 |
WRITING |
no registry entry but the transcript moved in the last two minutes | wait, then rescan |
STOPPED + interrupted work |
dead, with a run or an agent that was still going | recover it |
STOPPED + nothing interrupted |
idle when it died, or owed only long-abandoned runs | leave it, or --include-idle |
What ships with it
11 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.
- evals/evals.json 4.7 KB
- gemini.md 17 KB
- references/evidence.md 8.3 KB
- references/mechanics.md 14 KB
- scripts/grade_evals.py 5.6 KB runs code
- scripts/kill_orphans.py 7.1 KB runs code
- scripts/open_tabs.py 16 KB runs code
- scripts/promote_agent.py 5.3 KB runs code
- scripts/scan_crashed.py 19 KB runs code
- scripts/selftest.py 14 KB runs code
- scripts/splice_result.py 5.8 KB runs code
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.
- 1mo ago First seen · 281 lines · 239 tokens per session scan A e2965d47e227
recover-claude-code is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 239 tokens to every session and 3,897 once invoked, about $0.0010 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 2026-09-04.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.