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.
npx agentmods add commands/asheshgoplani/agent-deck/restartgit clone --depth 1 https://github.com/asheshgoplani/agent-deckWrote 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.
[](https://agentmods.dev/commands/asheshgoplani/agent-deck/restart)<a href="https://agentmods.dev/commands/asheshgoplani/agent-deck/restart"><img src="https://agentmods.dev/badge/commands/asheshgoplani/agent-deck/restart.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00857 |
| Opus 5 | $0.00000 | $0.00428 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
restart 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Restart & Context Preservation
Prepare for a fresh session by saving all current context, progress, and decisions.
Use this command when context is running low and you need to run /clear or restart Claude Code.
Instructions
1. Save Current Progress
Update .claude/plans/TO-DOS.md
Create or update .claude/plans/TO-DOS.md with current task status:
# Current Tasks
## In Progress
- [ ] [Current task being worked on]
## Completed This Session
- [x] [Task 1]
- [x] [Task 2]
## Pending
- [ ] [Next task]
- [ ] [Future task]
## Blocked
- [ ] [Blocked task] - Reason: [why blocked]
Update .claude/plans/DECISIONS.md
Create or update .claude/plans/DECISIONS.md with any decisions made:
# Architecture Decisions
## [Date] - [Decision Title]
**Context**: [Why this decision was needed]
**Decision**: [What was decided]
**Consequences**: [Impact of this decision]
2. Update Memory (MCP)
If using the memory MCP server, store key context:
Key entities to remember:
- Current feature being built
- Architectural decisions made
- Blockers encountered
- Next steps planned
3. Commit Current Work
IMPORTANT: Before clearing, commit all progress to git.
Run the /git:commit command or manually:
# Stage all changes
git add -A
# Create a work-in-progress commit
git commit -m "wip: [current feature] - saving progress before session restart
Current state:
- [What's working]
- [What's in progress]
- [What's next]"
# Push to remote
git push
4. Create Session Handoff
Write a brief summary to .claude/plans/SESSION-HANDOFF.md:
# Session Handoff - [Date/Time]
## What Was Accomplished
- [List of completed work]
## Current State
- Branch: `[branch-name]`
- Feature: [feature being built]
- Status: [percentage complete or description]
## Open Issues
- [Issue 1]
- [Issue 2]
## Next Steps (in order)
1. [Immediate next step]
2. [Following step]
3. [After that]
## Important Context
- [Key decision or insight]
- [Gotcha to remember]
- [File that needs attention]
## Commands to Run First
\`\`\`bash
npm install # if deps changed
npm run dev # start dev server
\`\`\`
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 · 168 lines · 0 tokens per session scan A 883620be3087
restart is a command published in the GitHub repository asheshgoplani/agent-deck (828 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 857 tokens. 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 2026-08-30.
Other commands, from other repositories
rosetta-grill
Grill the user about a plan or design — but grounded in Rosetta's resolved decision state — then RECORD the outcome as an ADR/PDR. Use when the user wants to stress-test a decision, says "grill me on this", or wants a decision interrogated and captured. Integrates grill-me-style interrogation with Rosetta's…
rosetta-conflicts
Surface decisions the library cannot uniquely resolve — unresolved conflicts (≥2 current records), code that contradicts an Accepted ADR, and stale records whose cited code moved on. Use to audit a decision library's health before trusting it, or when the user asks "what's contradictory / unresolved / stale in our…
rosetta-preflight
Produce Rosetta's deterministic preflight JSON for a scoped change: optional RA1 structural report, decision-state resolution, and local Rosetta gates. Use before handing execution to a loop runner.
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
init
Install the formatters this repository needs, with every command visible before it runs.