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/catchupgit clone --depth 1 https://github.com/asheshgoplani/agent-deckWhat 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 | $0.00576 |
| Opus 5 | $0.00000 | $0.00288 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade B, and why
catchup scanned grade B with 1 finding 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/plans/SESSION-HANDOFF.md 2>/dev/null || echo "No session handoff file" How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Restoration
Rebuild context after /clear or starting a new session.
Instructions
1. Check Git Status
# Current branch and status
git status
# Recent commits
git log --oneline -10
# Changes since last commit
git diff --stat
# Staged changes
git diff --cached --stat
2. Identify Current Work
- What branch are we on?
- What feature/task is in progress?
- Are there uncommitted changes?
- What was the last commit about?
3. Read Key Context Files
# Project guidelines
cat CLAUDE.md
# Session handoff (primary context restore)
cat .claude/plans/SESSION-HANDOFF.md 2>/dev/null || echo "No session handoff file"
# Recent decisions
cat .claude/plans/DECISIONS.md 2>/dev/null || echo "No decisions file"
# Current todos
cat .claude/plans/TO-DOS.md 2>/dev/null || echo "No todos file"
4. Summarize Recent Changes
Review recently modified files:
# Files changed in last 5 commits
git diff --name-only HEAD~5..HEAD
# Most recently modified files
ls -lt src/**/*.{ts,tsx} 2>/dev/null | head -10
5. Check for In-Progress Work
- Open TODOs in code (
grep -r "TODO" src/) - Failing tests (
npm run test:run) - Build errors (
npm run build)
Output Format
## Session Context Restored
### Current State
- Branch: `feature/xyz`
- Last commit: "feat: add email threading"
- Uncommitted changes: 3 files
### Session Handoff
[Summary from .claude/plans/SESSION-HANDOFF.md]
### In Progress
[Description of current work based on changes]
### Recent History
1. [Commit 1 summary]
2. [Commit 2 summary]
3. [Commit 3 summary]
### Open Tasks
- [ ] [Task from .claude/plans/TO-DOS.md]
### Key Decisions
- [Recent decisions from .claude/plans/DECISIONS.md]
### Next Steps
Based on the context, you should probably:
1. [Suggested next action]
2. [Suggested next action]
### Key Files to Review
- `src/components/X.tsx` - Recently modified
- `src/hooks/useY.ts` - In progress
Use After
- Running
/clear - Starting a new Claude Code session
- Returning after a break
- Switching between branches
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 · 107 lines · 0 tokens per session scan B cd84d75a441f
catchup is a command published in the GitHub repository asheshgoplani/agent-deck (813 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 576 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
todo
The quality-gated task list: tasks with real descriptions, testable acceptance criteria, and evidence — a task only closes when the controller agrees it is done.
release
The pre-tag controller: version sync, changelog, clean tree, gate, and suite — every failure listed, the tag printed, never run.
security
The security pass: secrets (blocking), SAST, dependency vulns — plus the index's entry points to review from.