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 teimurjan/lethe/plugin install letheWrote 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/teimurjan/lethe/recall)<a href="https://agentmods.dev/skills/teimurjan/lethe/recall"><img src="https://agentmods.dev/badge/skills/teimurjan/lethe/recall.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 | $0.00054 | $0.00665 |
| Opus 5 | $0.00027 | $0.00332 |
| Sonnet 5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a memory retrieval agent for lethe, a memory store that indexes your Claude Code / Codex transcripts directly, with hybrid BM25 + dense retrieval and clustered retrieval-induced forgetting.
Scope
This skill searches memories in the current project only. If the user references work from another repo, or asks a question that looks cross-project, use the recall-global skill instead.
Project namespace
Collection: !bash "${CLAUDE_PLUGIN_ROOT}/scripts/derive-collection.sh"
Memories are indexed straight from your Claude Code transcripts under $CLAUDE_CONFIG_DIR/projects (no .lethe/ is written into the repo). lethe search transparently reindexes any new or changed transcripts before searching, so recall always reflects the latest turns. Each hit is a raw user+assistant turn, not a summary.
Task
Find memories relevant to: $ARGUMENTS
Steps
-
Search. Run the CLI:
lethe search "<query>" --top-k 5 --json-output- If
letheis not on PATH, ask the user to install it:brew tap teimurjan/lethe && brew install lethe(macOS / Linuxbrew) orcargo install lethe-cli.
Output is JSON:
[{"id": "...", "content": "...", "score": 4.2}, ...]. Thecontentstarts with a<!-- session:… turn:… transcript:… -->anchor followed by theUSER:/ASSISTANT:turn body.By default this opens the project index read-write so it can index new turns and let retrieval-driven RIF state (suppression scores, tier promotion, retrieval counts) evolve. If you hit a "Conflicting lock" error because another lethe process holds the writer (parallel sessions), retry once with
--read-only— that skips the reindex + post-retrieve save and searches whatever was last indexed. -
Filter. Skip results that obviously don't match the user's question. A weak cross-encoder score (< 0) usually means a miss.
-
Expand. For the top 2–3 hits, run
lethe expand <id1> <id2> <id3>(multi-arg, single call) to see the full turn body. Output is plain text with=== <id> ===headers between chunks.
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 · 44 lines · 54 tokens per session scan A 61d7bdf7d323
recall is a skill published in the GitHub repository teimurjan/lethe (11 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 665 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.
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…
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.
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%.
pod-kb
Display the project knowledge base (lifecycle/kb.md) — project-specific patterns, decisions, and gotchas accumulated by CocoCupper across sessions.
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.
pull-search
CocoPull session archive search — full-text search across past sessions. Handles $pull search " " with --since and --feature filters, and $pull index rebuild.