recall-global

recall-global is a skill for Claude Code from teimurjan/lethe. It costs 64 tokens per session (654 once invoked), scanned A, original, MIT.

A memory-search skill for finding relevant information across all registered Lethe projects. Lethe is a memory store that indexes past Claude Code and Codex conversations.

In plain words
What is it for?
Use it to search past conversations across repositories and identify which project each result came from.
Why use it?
It helps recover decisions, debugging notes, and previous work when the information is in another project. This avoids relying on manual transcript searches or memory.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Part of the lethe plugin — 2 skills, 1 hook shipped together

Good fit Use it to search past conversations across repositories and identify which project each result came from.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/teimurjan/lethe/recall-global
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 teimurjan/lethe --skill recall-global
Clone the repo
git clone --depth 1 https://github.com/teimurjan/lethe

Made for: Claude Code.

Or install lethe, the plugin that ships this one along with the rest of its 2 skills, 1 hook.

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 recall-global

README.md
[![agentmods](https://agentmods.dev/badge/skills/teimurjan/lethe/recall-global/github.svg)](https://agentmods.dev/skills/teimurjan/lethe/recall-global)
Your own site
<a href="https://agentmods.dev/skills/teimurjan/lethe/recall-global"><img src="https://agentmods.dev/badge/skills/teimurjan/lethe/recall-global/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.

agentmods 80×15 button for recall-global

Your own site · 80×15
<a href="https://agentmods.dev/skills/teimurjan/lethe/recall-global"><img src="https://agentmods.dev/badge/skills/teimurjan/lethe/recall-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 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 $0.00064 $0.00654
Opus 5 $0.00032 $0.00327
Sonnet 5 $0.00013 $0.00131
Haiku 4.5 $0.00006 $0.00065

Measured 9d ago against content hash 04ebee213f5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

recall-global 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 9d 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/claude-code/skills/recall-global/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a memory retrieval agent for lethe, a memory store that indexes your Claude Code / Codex transcripts directly, with hybrid BM25 + dense retrieval and clustered retrieval-induced forgetting.

Scope

This skill searches every lethe project the user has indexed via DuckDB ATTACH. Every lethe index auto-registers a project in ~/.lethe/projects.json, so this sees everything the user has ever indexed. If the user only wants the current project, use the recall skill instead.

Task

Find memories relevant to: $ARGUMENTS

Steps

  1. Search. Run the CLI with --all:

    • lethe search "<query>" --all --top-k 5 --json-output
    • If lethe is not on PATH, ask the user to install it: brew tap teimurjan/lethe && brew install lethe (macOS / Linuxbrew) or cargo install lethe-cli.

    Output is JSON with per-project attribution: [{"id": "...", "content": "...", "score": 4.2, "project_slug": "...", "project_root": "..."}, ...].

    --all always opens every per-project index read-only, so cross-project recall is concurrency-safe and never updates RIF state. No --read-only opt-out is needed here. Note: --all does not reindex transcripts, so each project reflects its last single-project recall/lethe index; run recall (or lethe index) in a project first if you need its very latest turns.

  2. Filter. Skip results that obviously don't match the user's question. A weak cross-encoder score (< 0) usually means a miss.

  3. Expand. For the top 2–3 hits, run lethe --root <project_root> expand <id1> <id2> ... (multi-arg, single call). Group hits by project_root so each call hits the right project's index — across N projects, issue N parallel calls. Output is plain text with === <id> === headers between chunks.

  4. Summarize. Return a concise, source-referenced answer:

    • Quote or paraphrase the relevant fragments.
    • Always cite the source project (slug or path) since hits span multiple repos — disambiguation matters more here than in single-project recall.
    • Cite day / session within the project when it helps.
    • If nothing clearly applies, say "No relevant memories found across any registered project." — do not fabricate.

Read the full file on GitHub · 39 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. 9d ago First seen · 39 lines · 64 tokens per session scan A 04ebee213f5b

Subscribe to this mod's changes

recall-global is a skill published in the GitHub repository teimurjan/lethe (11 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 654 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

knowledge_store_skill

Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…

NPC-Worldwide/npcpy · 346 tokens

cocoscout

Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.

Snowflake-Labs/cocoplus · 59 tokens

cocohealth

Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.

Snowflake-Labs/cocoplus · 38 tokens

pull-search

CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.

Snowflake-Labs/cocoplus · 38 tokens

pod-kb

Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.

Snowflake-Labs/cocoplus · 33 tokens

pod-resume

Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.

Snowflake-Labs/cocoplus · 50 tokens