# AI use cases for Claude Flightdeck (scasella/claude-flightdeck)

Repo: [scasella/claude-flightdeck](https://github.com/scasella/claude-flightdeck) | Use cases: 4 | Page: https://dedupedai.com/use-cases/scasella-claude-flightdeck/

Flightdeck is a Claude Code mod that adds a live dashboard to your terminal showing context, cost, permission checks, advisor consults and subagents.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Watch context, cost and rate limits during a session: https://dedupedai.com/use-cases/scasella-claude-flightdeck/watch-context-and-cost-live/
- Audit every permission check a session makes: https://dedupedai.com/use-cases/scasella-claude-flightdeck/audit-permission-checks-in-a-session/
- Follow subagents as cards or swimlanes: https://dedupedai.com/use-cases/scasella-claude-flightdeck/track-subagents-as-cards-or-swimlanes/
- Review architect and advisor consults in a session: https://dedupedai.com/use-cases/scasella-claude-flightdeck/review-architect-advisor-consults/

## How to watch context, cost and rate limits during a session with Claude Flightdeck

Repo: [scasella/claude-flightdeck](https://github.com/scasella/claude-flightdeck) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Keep the main panel open to see context fill, compactions, cost and rate-limit resets as you work.

**Who it is for:** A developer running a long Claude Code session who needs to know how close the context window and plan limits are getting.

**The problem:** Context, cost and rate-limit readings are scattered or hidden during a long session, so it is hard to tell when to compact, slow down or split the work.

**The outcome:** A docked pane beside the transcript showing model, effort, permission mode, the context gauge with compactions, cost, and the first two rate-limit windows with time to reset.

### Steps

1. Inside Claude Code, run `/plugin marketplace add scasella/claude-flightdeck`
2. Run `/plugin install flightdeck@claude-flightdeck`
3. Run `/reload-plugins`
4. Run `/flightdeck` to open the pane
5. Read the main panel's context gauge and cost while you work; run `/flightdeck reset` to clear agents, checks, consults and log while keeping cost and rate limits

### Prompt to paste into your agent

```text
In Claude Code 2.1.287 or later, install the scasella/claude-flightdeck plugin from its marketplace, run /reload-plugins and /flightdeck, then report the model, context percentage, compaction count and cost shown in the main panel. Verify the main panel appears before reporting.
```

### Caveat

The cost and rate-limit figures show only when your plan reports them, and Flightdeck itself makes no network requests and calls no model.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/scasella-claude-flightdeck/watch-context-and-cost-live/

## How to audit every permission check a session makes with Claude Flightdeck

Repo: [scasella/claude-flightdeck](https://github.com/scasella/claude-flightdeck) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Use the gate panel and its drill-downs to see which tools were allowed, asked about or denied.

**Who it is for:** A developer or team lead reviewing what an agent session was allowed to do, or checking why a tool call was blocked.

**The problem:** Permission verdicts pass by quickly, so it is hard to tell which tool calls ran without asking, which were decided by the classifier or the user, and which were denied.

**The outcome:** A gate panel with one colored cell per permission check, totals, and per-family drill-downs listing the last five checks and their verdicts with credentials masked.

### Steps

1. Install the plugin with `/plugin marketplace add scasella/claude-flightdeck` and `/plugin install flightdeck@claude-flightdeck`
2. Run `/reload-plugins` and `/flightdeck`
3. Press `ctrl+x tab` to focus the pane
4. Press `f`, `s` or `o` to open the file, shell or other drill-down and read the last five checks and their verdicts
5. Note any red denied cells and any checks made inside a subagent (dimmed) before finishing the session

### Prompt to paste into your agent

```text
Install the scasella/claude-flightdeck plugin in Claude Code 2.1.287 or later, open /flightdeck, focus the pane with ctrl+x tab, and open the file drill-down with f. Report the number of allowed, denied and pending checks shown in the gate panel, and confirm credentials appear masked.
```

### Caveat

The gate records short summaries of checks in session state only, which ends with the session, so older sessions cannot be audited from the pane.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/scasella-claude-flightdeck/audit-permission-checks-in-a-session/

## How to follow subagents as cards or swimlanes with Claude Flightdeck

Repo: [scasella/claude-flightdeck](https://github.com/scasella/claude-flightdeck) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

See each subagent's task, live context, output tokens, steps and clock, and expand any one for detail.

**Who it is for:** A developer running a Claude Code session that spawns several subagents who needs to see which ones are running, stalled or hitting max_tokens.

**The problem:** Subagents run in parallel and their progress is hard to follow from the transcript alone, especially when one stalls or hits its token limit.

**The outcome:** An agents panel showing cards side by side while they fit, or swimlanes on one time axis beyond that, with the max_tokens warning in red and expandable detail for each agent.

### Steps

1. Install the plugin with `/plugin marketplace add scasella/claude-flightdeck` and `/plugin install flightdeck@claude-flightdeck`
2. Run `/reload-plugins` and `/flightdeck`
3. Start a session that spawns subagents and watch the agents panel fill with cards
4. Press `ctrl+x tab`, then `1`, `2` and so on to expand a card or lane and read its last three tool calls and the start of its answer
5. Set `maxCards` in `/config` (1 to 6) if you want swimlanes to appear sooner

### Prompt to paste into your agent

```text
Install the scasella/claude-flightdeck plugin in Claude Code 2.1.287 or later, start a task that spawns at least two subagents, and open /flightdeck. Report how many agents appear as cards or swimlanes and flag any agent showing max_tokens in red. Verify the expanded view of one agent shows its last three tool calls.
```

### Caveat

Per-agent context is the latest request's full input and is labelled ctx, not cost, because the API reports no per-agent cost.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/scasella-claude-flightdeck/track-subagents-as-cards-or-swimlanes/

## How to review architect and advisor consults in a session with Claude Flightdeck

Repo: [scasella/claude-flightdeck](https://github.com/scasella/claude-flightdeck) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Check when the architect or advisor was consulted, how long each took, and what the inferred moments were.

**Who it is for:** A developer who relies on an architect or advisor agent in Claude Code and wants to confirm when it was consulted and whether it helped.

**The problem:** It is unclear how often the architect was consulted, how long those consults took, and whether a server-side advisor was used at all.

**The outcome:** An architect panel with a consult timeline, a running or last-consult duration, optional consult moments labelled as inferred, and the first line of a subagent architect's advice.

### Steps

1. Install the plugin with `/plugin marketplace add scasella/claude-flightdeck` and `/plugin install flightdeck@claude-flightdeck`
2. Run `/reload-plugins` and `/flightdeck`
3. Read the architect panel's consult timeline and how long the last consult took
4. Check which moments are marked `(inferred)`; set `moments` to `false` in `/config` to hide them
5. If your architect has a different name, change `architectPattern` in `/config` to match its agent type or server tool

### Prompt to paste into your agent

```text
Install the scasella/claude-flightdeck plugin in Claude Code 2.1.287 or later, run a task that consults an architect or advisor, and open /flightdeck. Report the number of consults on the architect timeline and the duration of the last one. Verify that any moment labelled (inferred) is distinguished from measured consults.
```

### Caveat

Server-side advice from a tool such as Claude Code's advisor is encrypted, so the pane shows only the count and timing of consults, not what they said.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/scasella-claude-flightdeck/review-architect-advisor-consults/