Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add codika-io/clave/plugin install claveWrote 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/codika-io/clave/recover-sessions)<a href="https://agentmods.dev/skills/codika-io/clave/recover-sessions"><img src="https://agentmods.dev/badge/skills/codika-io/clave/recover-sessions.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 | $0.00075 | $0.02081 |
| Opus 5 | $0.00037 | $0.01040 |
| Sonnet 5 | $0.00015 | $0.00416 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade B, and why
recover-sessions scanned grade B with 1 finding 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Retention is a **local** setting, `cleanupPeriodDays` in `~/.claude/settings.json` (default 30 days). It is not a server-side policy — nothing is fetched from Anthropic and nothing expires in the cloud. If the user's set How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recover Sessions
Clave tabs are disposable; the conversations behind them are not. Claude Code writes every session to a local transcript file that survives an app crash, a machine reboot, and Clave's own state being wiped. This skill finds those transcripts, works out what each session was about, and rebuilds the user's groups and tabs with the real conversations restored — not empty tabs.
Use it when the user says any of: "I lost my sessions", "my computer crashed, get my workspace back", "what was I working on?", "recover what I had".
What the user gets back
Their history, verbatim. claude --resume <session-id> reopens a session with its full context, so a recovered tab picks up exactly where it stopped. What is genuinely lost is only Clave's own arrangement — which group a tab sat in and what it was called — and that is what you reconstruct from evidence plus the user's memory.
Where the transcripts live
~/.claude/projects/<path-encoded-cwd>/<session-uuid>.jsonl
One JSONL file per session; the filename stem IS the session id you resume with. The directory name is the session's working directory with / replaced by -.
Retention is a local setting, cleanupPeriodDays in ~/.claude/settings.json (default 30 days). It is not a server-side policy — nothing is fetched from Anthropic and nothing expires in the cloud. If the user's setting is low and they care about recovery, mention raising it; that is the whole fix.
Step 1 — Ask what they remember, briefly
Before scanning, get the user's own picture in one short exchange: roughly how many groups, what the big ones were about, and when they were last working. Do not interrogate them. Vague answers are fine and normal ("one group for the mobile app, a big one for the API rewrite, and something about billing") — the scan supplies the precision, their memory supplies the grouping and the names.
If they cannot remember anything, skip straight to the scan and present what you find, newest first.
What ships with it
1 file 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.
- 6d ago First seen · 131 lines · 75 tokens per session scan B 0b9df731d9ac
recover-sessions is a skill published in the GitHub repository codika-io/clave (47 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 2,081 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
warpctrl
Control and inspect the currently running local Warp application with the warpctrl CLI. Use this skill whenever the user asks the agent to manipulate Warp's own windows, tabs, panes, sessions, input buffer, themes, or UI surfaces; open a file in Warp; inspect local Warp state; or explain how to invoke Warp Control…
change-keybinding
Customize Warp keyboard shortcuts (keybindings, keymappings) by editing the user's keybindings.yaml file. Use when the user asks to remap a key combination, rebind an action, change a shortcut, or remove a default keybinding (e.g. "change ctrl+space to ctrl+s", "rebind the command palette to cmd+p", "remove the…
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…
create-tab-config
Create new Warp tab config TOML files from natural-language requests. Use when the user wants a new tab config, a new tab layout, or asks for a slash command to generate a tab config.
liney-cli
Use the Liney CLI (liney) to inspect or control a running Liney terminal workspace and the agent sessions it hosts. Liney runs several coding agents in parallel, each in its own pane/tab/worktree, so reach for this whenever the user wants to act on a pane other than the current one — check on, coordinate, read from…
meditate
End-of-session reflection generating persistent learnings about user preferences, communication patterns, and cross-session insights. Activates when wrapping up a session, or when user says "let's wrap up", "end the session", "time to reflect", or "meditate". Also extracts judgment rules from decisions made during the…