reset

A command that closes the current coding session, saves its notes, clears the conversation, and starts a fresh project review.

In plain words
What is it for?
Use it after a long session, a large merge or rebase, a switch to another part of the codebase, or when starting a specific task with a clean project overview.
Why use it?
It helps when the agent is forgetting files, relying on outdated context, or the session has become too long to follow reliably.

Command for Claude Code

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 commands/codeverbojan/claude-code-kickstart/reset
Clone the repo
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstart

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00257
Opus 5 $0.00009 $0.00129
Sonnet 5 $0.00004 $0.00051
Haiku 4.5 $0.00002 $0.00026

Measured yesterday against content hash a08a31f8a8ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reset 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 yesterday.

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.

.claude/commands/reset.md · 33 lines

What it actually says

Reset Session

Three phases, in order. Don't skip.

Phase 1: Wrap up

Run the full /wrap-up flow: verify, rewrite primer.md, update decisions.md/gotchas.md/metrics.jsonl. Don't report to the user yet.

Phase 2: Clear context

Tell the user: "Session state saved. Clearing context and restarting fresh." Then run /clear.

Phase 3: Deep onboard

The SessionStart hook auto-loads primer.md (and any non-stub gotchas/patterns/decisions) on session resume. Then run /onboard deep to get the full project explore + status report.

If the user provided a task with /reset, pass it through to /onboard deep so the onboard focuses on that task.

When to use

  • Context is degraded (forgetting files, editing stale content, hallucinating).
  • Switching to a completely different area of the codebase.
  • After a long session (20+ messages).
  • After a large merge or rebase.

$ARGUMENTS

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. yesterday First seen · 33 lines · 18 tokens per session scan A a08a31f8a8ed

Subscribe to this mod's changes

reset is a command published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 257 once invoked, about $0.0001 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.