Agent Deck is a terminal session manager that lets developers monitor and switch between multiple AI coding-agent sessions from one text interface. It helps people organize agents working across projects with groups, search, forking, Git worktrees, cost tracking, and a phone-controlled conductor. The catalogue entries extend its use with skills, commands, and a plugin.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/asheshgoplani/agent-decknpx agentmods add skills/asheshgoplani/agent-deck/fleetWrote 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/skills/asheshgoplani/agent-deck/fleet)<a href="https://agentmods.dev/skills/asheshgoplani/agent-deck/fleet"><img src="https://agentmods.dev/badge/skills/asheshgoplani/agent-deck/fleet/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asheshgoplani/agent-deck/fleet"><img src="https://agentmods.dev/badge/skills/asheshgoplani/agent-deck/fleet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 165 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00094 | $0.04191 |
| Opus 5.5 | $0.00038 | $0.01676 |
| Sonnet 5.5 | $0.00019 | $0.00838 |
| Haiku 4.5 | $0.00009 | $0.00419 |
Grade A, and why
fleet 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 16d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet
Fan out several independent agent-deck child sessions from inside your current session, keep working, and check their progress on demand — without blocking and without consuming any delivery events.
Requires: the agent-deck session children and launch --assert-done
features. If agent-deck session children --help succeeds, you have them.
When to use
Use this when the user wants more than one agent working at once and wants to supervise from the parent session — e.g. "launch 5 sessions to each tackle a file", "fan out these tasks", "spin up a fleet and tell me when they're done".
This differs from the single sub-agent pattern in the agent-deck skill (one
child + fire-&-forget / on-demand / blocking retrieval). Fleet is many
children + a non-blocking peek across all of them.
Run from inside an agent-deck session. Launching auto-parents each child to the launching session, which is what makes them show up nested in the TUI and routes their completion back to you. (If you are not in a session, the children still launch but won't be grouped under a parent.)
Need a specific parent? Auto-parenting picks the launching session. To
parent a child to a different session — e.g. fanning out under a named conductor,
or launching from outside that session — pass --parent <session-id-or-title>.
Spell out the long form: never use the short -p to set a parent (see the
-p pitfall in Notes).
Before you fan out
- Check for shared singletons. N sessions on the same project can't truly run in parallel if they serialize on one resource — a single dev DB, a bound port, one dev-server lock file. If they'd share one, either give each child isolated resources (own DB name + port) or run one coherent session instead of a fleet.
- Worktree children need deps installed first. A freshly created git worktree
has no
node_modules/ vendored deps. Make the first instruction in the child's-mprompt install them — and for a locked monorepo, install from the frozen lockfile, never regenerate it (e.g.pnpm install --frozen-lockfile). Otherwise the child's first test/build/e2e fails confusingly. - Long prompts: pass via a file. For a big multi-line task, write it to a
file and pass
--message-file task.md(or--message-file -to read stdin) instead of-m. The file is read directly by agent-deck, so backticks,$, and quotes never round-trip through the shell. Also works onsession startandsession send(there it replaces the positional message). On older builds without the flag, fall back to-m "$(cat task.md)".
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed f8a0f930f300
- 1mo ago Changed · +8 lines 57d57e0d9a00
- 1mo ago First seen · 304 lines · 94 tokens per session scan A 5a32bd42d94d
fleet is a skill published in the GitHub repository asheshgoplani/agent-deck (1,111 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 4,191 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
agnix
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 702 rules across 10+ AI tools.
fast-resume
Search local coding-agent session history and identify safe resume commands. Use when the user asks to find, inspect, continue, or recover previous work from Claude Code, Codex, Pi, or another agent indexed by fast-resume.
agent-team-protocol
Multi-agent delegation rules, three-phase workflow (Plan/Build/Review), model selection, collaboration gates, and Ralph Loop integration.
opus-4-7-features
Optional guidance for sessions using Claude Opus 4.7: adaptive thinking, xhigh effort, prompt caching, /btw side questions.
phase-workflow
Phase transition rules, post-phase verification steps, peer review validation, and commit-gate approval flow.
copilot-conventions
Cross-copilot portable conventions: target alignment, complexity control, minimal changes, git discipline, and project structure.