A session-start hook that runs a JavaScript handler when Claude Code begins a session. It uses Bun when available and otherwise falls back to Node.

Starting the plugin’s session initialization process whenever a new Claude Code session opens.

It automates an action at the beginning of each session instead of requiring a manual command.

forget — Skill by ThisisYoYoDev

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/thisisyoyodev/claude-rag/forget

Any agent

npx skills add ThisisYoYoDev/claude-rag --skill forget

Clone the repo

git clone --depth 1 https://github.com/ThisisYoYoDev/claude-rag

Made for: Claude Code, Codex.

Or install claude-rag, the plugin that ships this one along with the rest of its 9 skills, 19 commands, 6 hooks, 1 MCP server.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 438 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 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	$0.00025	$0.00438
Opus 5	$0.00013	$0.00219
Sonnet 5	$0.00005	$0.00088
Haiku 4.5	$0.00003	$0.00044

Measured 3d ago against content hash 6726759d2963, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

forget scanned grade B with 2 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}'

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(curl *), AskUserQuestion

skills/forget/SKILL.md · 56 lines

What it actually says

RAG Forget (Soft Delete)

Delete data from the RAG database. Data is soft-deleted and can be restored.

Instructions

Read the plugin config:

cat ~/.claude/plugins/claude-rag/config.json 2>/dev/null || echo '{"connection":{"endpoint":"https://api.clauderag.io"}}'

Determine scope from "$ARGUMENTS":

No argument → Ask the user

Use AskUserQuestion:

question: "What do you want to forget?"
options: ["A specific session", "An entire project", "Everything"]

"all" → Confirm then delete all projects

Always confirm first with AskUserQuestion:

question: "This will soft-delete ALL your RAG data. Are you sure?"
options: ["Yes, delete everything", "No, cancel"]

If confirmed, list all projects and delete each:

curl -s <endpoint>/api/v1/projects
# For each project:
curl -s -X DELETE <endpoint>/api/v1/projects/<id>

Session ID (UUID) → Delete that session

curl -s -X DELETE <endpoint>/api/v1/sessions/<id>

Project name → Find and delete project

curl -s <endpoint>/api/v1/projects
# Find matching project, then:
curl -s -X DELETE <endpoint>/api/v1/projects/<id>

After deletion, show:
- What was deleted (session name, project name, event counts)
- Remind: "Data is soft-deleted and can be restored with /claude-rag:restore"
Never hard-delete. Always use the DELETE endpoints which perform soft-delete.

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.

3d ago First seen · 56 lines · 25 tokens per session scan B 6726759d2963

Subscribe to this mod's changes

forget is a skill published in the GitHub repository ThisisYoYoDev/claude-rag (9 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 438 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Memory and context RAG and vectors

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

9router-embeddings

Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.

decolua/9router · 66 tokens

potpie-source-ingestion

Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…

potpie-ai/potpie · 82 tokens

forget