A command that shows compact context for resuming work on a project. It collects the last session summary, active tasks, open bugs, recent decisions, and a suggested next action.

Use it at the start of a session to review unfinished work, blockers, bugs, and recent technical decisions.

It reduces the time spent reconstructing where work stopped, especially after switching projects or returning later.

where-was-i — Command for Claude Code by IvanLutsenko

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add IvanLutsenko/awac-ai-agent-plugins

Claude Code

/plugin install obsidian-tracker

Made for: Claude Code.

Or install obsidian-tracker, the plugin that ships this one along with the rest of its 19 skills, 19 commands.

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/commands/ivanlutsenko/awac-ai-agent-plugins/where-was-i.svg)](https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/where-was-i)

Your own site

<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/where-was-i"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/where-was-i.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 515 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00015	$0.00515
Opus 5	$0.00008	$0.00258
Sonnet 5	$0.00003	$0.00103
Haiku 4.5	$0.00002	$0.00052

Measured 2d ago against content hash f5d22a3adf8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

where-was-i 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 2d 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/obsidian-tracker/commands/where-was-i.md · 70 lines

What it actually says

/where-was-i — Resume Context

Goal

Show the user a compact context block to quickly resume work on a project.

Steps

Determine project:
- If .claude/obsidian-tracking.json exists, use the project from it.
- Otherwise, call findProjectByLocalPath with the current working directory.
- If still no project, call listProjects and ask the user which project.
Get resume context:
- Call getResumeContext with the resolved project name.
Format output as a compact block:

# Resume Context for {project}

## Current Focus
{suggestedAction}

## Last Session ({date})
Completed:
- {items}

Blockers: {items or "None"}

## Active Work
Tasks:
- [{status}] {title}

Bugs:
- [{priority}] {title}

## Recent Decisions
- {DEC-id}: {title}

Keep it token-efficient:
- No descriptions, only titles and statuses.
- Target ~300-500 tokens max.
- If a section is empty, show "None" on one line, don't skip the section.
If no data exists (no summaries, no tasks, no bugs):
- Say "No previous session data found for {project}. This looks like a fresh start."
Auto-start tracking: If .claude/obsidian-tracking.json does not exist, start tracking for the resolved project:
```
${CLAUDE_PLUGIN_ROOT}/scripts/start-tracking.sh "{project}"
```

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.

2d ago First seen · 70 lines · 15 tokens per session scan A f5d22a3adf8a

Subscribe to this mod's changes

where-was-i is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 15 tokens to every session and 515 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 2026-09-05.

Project management

where-was-i

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/where-was-i — Resume Context

Goal

Steps

What this file has done since we first saw it

Other commands, from other repositories

template

sync-linear

add-note

fest-show

dispatcher

workpm