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 Snowflake-Labs/cocoplus --skill recallgit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/recall)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/recall"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/recall/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/snowflake-labs/cocoplus/recall"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/recall.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 | $0.00035 | $0.01591 |
| Opus 5 | $0.00017 | $0.00796 |
| Sonnet 5 | $0.00007 | $0.00318 |
| Haiku 4.5 | $0.00003 | $0.00159 |
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 8d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You are executing a CocoRecall command. CocoRecall's mandate is strict: retrieve evidence with citations; do not synthesize or interpret. Returning a summarized or reworded version of retrieved content is a second instance of the self-oracle failure mode applied to historical knowledge — it lets the querying agent's current framing shape what "the past" appears to say. Always surface verbatim turn excerpts with full citation metadata. The developer synthesizes; CocoRecall retrieves.
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus is not initialized. Run $pod init first." Then stop.
CocoRecall is entirely local. No session data is transmitted anywhere. recall.db lives at .cocoplus/recall.db (gitignored) and is rebuilt from source transcripts at ~/.snowflake/cortex/conversations/ on any machine via $recall import.
Commands
$recall search <query> [--all] [--session <id>] [--function <name>] [--outcome-type <type>]
Use the cocorecall/recall-import contract to search the normalized index using a three-factor relevance score: lexical match (query terms against turn text and entity tags), recency (decay-weighted), and phase context match (turns from the current CocoPlus phase rank higher).
Default behavior is session-diverse: return the single highest-relevance turn from each matching session, so one verbose session cannot dominate the results. --all returns every matching turn across all sessions. --session <id> restricts the search to one session. --function <name> filters to sessions that touched a function. --outcome-type <type> filters to sessions with matching outcome-contract evidence.
Every result carries four mandatory citation fields — never omit any of them:
- Session ID — the Snowflake Coco session identifier (source transcript at
~/.snowflake/cortex/conversations/<session-id>) - Turn ID — the specific turn within the session
- Source Exists — boolean, checked at retrieval time (not index time) against the actual transcript path
- Suggested Follow-Up — a query recommendation built from the retrieved turn's entity tags ("search for
<entity>to find related decisions in other sessions")
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.
- 8d ago First seen · 101 lines · 35 tokens per session scan A e3cbb5846781
recall is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 1,591 once invoked, about $0.0002 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 2026-09-03.
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…
remember
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Supports recording architectural decisions, anti-patterns, tool preferences, workflow outcomes, and project conventions that persist across sessions. Use when saving patterns, remembering…
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
authoring-claude-md
Creating and maintaining CLAUDE.md project memory files and .claude/rules/ rule files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't…
screenpipe-chats
Search what was said in existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats, then continue or steer one exact chat when the user explicitly asks. Use for requests about finding another agent conversation, recalling what an agent said, or sending work to one.
bootstrap-agent-identity
Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who…