A way to save one durable fact, decision, convention, or useful reference in a personal Trove, which is an indexed collection of notes for future sessions.

Recording things the user explicitly wants remembered, such as project conventions, decisions, gotchas, or external references.

It keeps important context from being lost when a conversation ends and avoids creating duplicate notes.

remember — Skill for Claude Code and Codex by anishfyi: A way to save one durable fact, decision, convention…

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.

agentmods

npx agentmods add skills/anishfyi/trove/remember

Any agent

npx skills add anishfyi/trove --skill remember

Clone the repo

git clone --depth 1 https://github.com/anishfyi/trove

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/anishfyi/trove/remember.svg)](https://agentmods.dev/skills/anishfyi/trove/remember)

Your own site

<a href="https://agentmods.dev/skills/anishfyi/trove/remember"><img src="https://agentmods.dev/badge/skills/anishfyi/trove/remember.svg" alt="Measured on agentmods" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 932 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00065	$0.00932
Opus 5	$0.00032	$0.00466
Sonnet 5	$0.00013	$0.00186
Haiku 4.5	$0.00006	$0.00093

Measured 4d ago against content hash 2784498f2bde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remember 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 4d 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/remember/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remember (capture into the Trove)

Persist one durable, atomic fact into the trove. One file per fact, indexed in INDEX.md.

Steps

Resolve the trove directory. Prefer a project trove if present, else the user trove:
- If ./.claude/trove/INDEX.md exists, use ./.claude/trove.
- Else if ~/.claude/trove/INDEX.md exists, use ~/.claude/trove.
- Else there is no trove yet: run the /trove:init skill first (or offer to), then continue.
Distill to one atomic fact. Compress the thing worth remembering into a single, self-contained entry. If the user hands you several things, write several entries.
Dedupe. Read INDEX.md. If an existing entry already covers this, update that file instead of creating a near-duplicate. Delete entries that have become wrong.
Choose the format, then write the entry. Two formats are supported; you decide by the shape of the content, every time:
- Markdown (entries/<slug>.md) when the content is prose: a decision and its rationale, a gotcha, a convention, any narrative worth a paragraph or two.
- JSON (entries/<slug>.json) when the content is structured data: a mapping, a list of records, a config snapshot, an API/endpoint table, a schema, anything where the structure is the point and prose would only get in the way.
When in doubt, prefer Markdown. Both formats carry the same top-level fields so every skill agrees.

Markdown template:
```
---
title: <Human readable title>
slug: <kebab-case-slug>
type: decision | gotcha | preference | reference | project | snippet
created: <YYYY-MM-DD>     # use today's date
tags: [tag1, tag2]
---

<One or two short paragraphs: the durable thing worth keeping.>

**Why it matters:** <when this applies / why it will matter later>
**Related:** [[other-slug]]    # link related entries; a not-yet-written slug is fine
```
JSON template (put the structured payload under data):

Read the full file on GitHub · 86 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.

4d ago First seen · 86 lines · 65 tokens per session scan A 2784498f2bde

Subscribe to this mod's changes

remember is a skill published in the GitHub repository anishfyi/trove (1 stars, last pushed 9d ago), licensed MIT. It adds 65 tokens to every session and 932 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.

Memory and context claude-code claude-code-plugin context-engineering developer-tools knowledge-management markdown

setup

Scaffold a complete knowledge system. Detects platform, conducts conversation, derives configuration, generates everything. Validates against 15 kernel primitives. Triggers on "/setup", "/setup --advanced", "set up my knowledge system", "create my vault".

agenticnotetaking/arscontexta · 53 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

architect

Research-backed evolution advice for your knowledge system. Analyzes health reports, friction patterns, and derivation history to propose specific changes with research justification. Never auto-implements — proposals require your approval.

agenticnotetaking/arscontexta · 42 tokens

health

Run condition-based vault health diagnostics. 8 categories — schema compliance, orphan detection, link health, description quality, three-space boundaries, processing throughput, stale notes, MOC coherence. 3 modes — quick (schema+orphans+links), full (all 8), three-space (boundary violations only). Returns actionable…

agenticnotetaking/arscontexta · 100 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

refactor

Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor", "restructure vault".

agenticnotetaking/arscontexta · 43 tokens