attune-ai: Skill for Claude Code

.agents/skills/recall/SKILL.md

recall is a skill for Claude Code, Codex from Smart-AI-Memory/attune-ai. It costs 46 tokens per session (1,915 once invoked), scanned A, original, Apache-2.0.

A memory search tool for retrieving findings from earlier coding sessions and a project's accumulated engineering lessons. It can search for a topic or show recent session findings.

In plain words
What is it for?
Use it to recall what was discovered about a bug, system, or technical topic in past sessions. It searches both saved session notes and the project's lessons when given a query.
Why use it?
It helps recover useful context that is no longer in the current conversation. This can prevent repeating investigations or overlooking lessons learned before.

Skill for Claude CodeCodex

Written for Claude Code: SessionStart hook event. Also seen: names the AskUserQuestion tool; mentions Claude Code; installed under .agents/ (shared by several agents).

This is Smart-AI-Memory/attune-ai's own configuration. It tells Claude Code and Codex how to work on attune-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything attune-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/recall/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Made for: Claude Code, Codex.

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

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

agentmods 80×15 button for recall

Your own site · 80×15
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/recall"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,915 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00046 $0.01915
Opus 5 $0.00023 $0.00958
Sonnet 5 $0.00009 $0.00383
Haiku 4.5 $0.00005 $0.00192

Measured 9d ago against content hash c617648ed17b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 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.

.agents/skills/recall/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recall

IMPORTANT: Start your response by telling the user:

Recall — Searching cross-session memory for findings related to your query.

What It Does

/recall is the on-demand companion to the automatic SessionStart recall. It searches TWO stores and labels results by source:

  1. Session findings — stashed by the Stop hook across past sessions (file backend by default; Redis AMS when connected).
  2. The lessons corpus — the repo's accumulated engineering lessons, retrieved via attune.lessons.LessonsIndex (query mode only; lessons have no recency, so the no-query mode skips them).
  • With a query (/recall AMS event loop): both stores; session findings keyword + recency ranked, lessons by retrieval score.
  • No query (/recall): the most recent session findings for this project.

Pick Your Transport First

Route by what YOUR client can actually do — never assume the universal Python recipe works everywhere (in a sandboxed provider it selects an unwritable file tier or a blocked socket):

  1. MCP available — the session_memory_* tools appear in your tool list (Codex, Claude Code with the attune MCP server, any MCP client): use them. They execute host-side, outside your sandbox, and carry the full contract (sanitization, cwd scoping, TTL). Never run in-process Python for memory from a sandboxed client, and never substitute raw redis_memory_store for finding capture — capture goes through session_memory_capture only.
  2. Trusted host context, no MCP — you can run repo Python directly (Claude Code Bash, the CLI, lifecycle hooks): the Python snippets below remain valid.
  3. Neither — report honestly that cross-session memory is unavailable in this client (no MCP tools, no trusted Python). Do not fake results and do not claim the backing service is down — you cannot know that from here.

MCP Tools

Tool Use
session_memory_recall Semantic search (args: query, optional top_k, cwd)
session_memory_recent Newest findings, no query (args: top_k, cwd)
session_memory_capture Stash a finding (args: content, type, tags, cwd)
session_memory_forget Delete by full record id (args: ids, cwd)
session_memory_status Caller-scoped backend status

Read the full file on GitHub · 179 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 · 179 lines · 46 tokens per session scan A c617648ed17b

Subscribe to this mod's changes

recall is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,915 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 2026-08-31.