recall

recall is a skill for Claude Code from anishfyi/trove. It costs 63 tokens per session (437 once invoked), scanned A, original, MIT.

A skill for searching a personal collection of saved notes, called a Trove. It reads matching entries and uses them to answer questions with references to the notes.

In plain words
What is it for?
Finding past decisions, personal knowledge, project notes, and earlier learnings about a topic.
Why use it?
It avoids guessing what was previously learned or decided by checking the stored notes directly. If no matching notes exist, it reports that plainly.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the trove plugin — 5 skills, 2 hooks shipped together

Good fit Finding past decisions, personal knowledge, project notes, and earlier learnings about a topic.

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

Made for: Claude Code.

Or install trove, the plugin that ships this one along with the rest of its 5 skills, 2 hooks.

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/anishfyi/trove/recall/github.svg)](https://agentmods.dev/skills/anishfyi/trove/recall)
Your own site
<a href="https://agentmods.dev/skills/anishfyi/trove/recall"><img src="https://agentmods.dev/badge/skills/anishfyi/trove/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/anishfyi/trove/recall"><img src="https://agentmods.dev/badge/skills/anishfyi/trove/recall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 437 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 $0.00063 $0.00437
Opus 5 $0.00032 $0.00218
Sonnet 5 $0.00013 $0.00087
Haiku 4.5 $0.00006 $0.00044

Measured 8d ago against content hash 119f8ca5cabf, 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 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.

plugins/trove/skills/recall/SKILL.md · 35 lines

What it actually says

Recall (search the Trove)

Answer a question using what is stored in the trove, grounded in the actual entry files.

Steps

  1. Resolve the trove directory (same rule as remember):

    • ./.claude/trove if it has an INDEX.md, else ~/.claude/trove.
    • If neither exists, tell the user there is no trove yet and offer /trove:init.
  2. Scan the index. Read INDEX.md. Use the one-line hooks (and grep over entries/ for keywords and tags) to find candidate entries. Entries may be .md or .json, so grep both.

  3. Open the relevant entries. Read the matching entries/<slug>.md or entries/<slug>.json files in full. Do not answer from the index hooks alone; the body holds the real content. For a JSON entry, the structured payload lives under its data key, parse and read it.

  4. Synthesize an answer grounded in those entries. Cite the entries you used by title or slug so the user can open them. If entries conflict or look stale (old created date, references a file that no longer exists), say so rather than asserting confidently.

  5. If nothing matches, say so plainly, give your best general answer, and offer to capture the new learning with /trove:remember.

Recalled entries reflect what was true when written. If an entry names a file, flag, or command, verify it still exists before recommending it.

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. 8d ago First seen · 35 lines · 63 tokens per session scan A 119f8ca5cabf

Subscribe to this mod's changes

recall is a skill published in the GitHub repository anishfyi/trove (1 stars, last pushed 13d ago), licensed MIT. It adds 63 tokens to every session and 437 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 2026-08-31.

Related

Other skills, from other repositories

okf

Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…

scaccogatto/okf-skills · 127 tokens

rethink

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

agenticnotetaking/arscontexta · 51 tokens

graph

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

agenticnotetaking/arscontexta · 50 tokens

remember

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

agenticnotetaking/arscontexta · 40 tokens

seed

Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".

agenticnotetaking/arscontexta · 49 tokens

orient

Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…

harnessprotocol/harness-kit · 80 tokens