fleet

A read-only roster showing active Claude Code sessions together with their project, branch, work context, governance state, and selected workflow or merge-readiness information.

In plain words
What is it for?
Use it to supervise many concurrent sessions and see their associated epics, atoms, decisions, blockers, isolation, gates, and workflow stages.
Why use it?
It gives an operator one view of parallel sessions without replacing Claude Code’s own session list.

Skill for Claude CodeCodex

Part of the foundry plugin — 47 skills, 8 agents, 8 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/lukasrepublic/agentic-foundry/fleet
Any agent
npx skills add lukasrepublic/agentic-foundry --skill fleet
Clone the repo
git clone --depth 1 https://github.com/lukasrepublic/agentic-foundry

Made for: Claude Code, Codex.

Or install foundry, the plugin that ships this one along with the rest of its 47 skills, 8 agents, 8 hooks, 1 MCP server.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 856 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00083 $0.00856
Opus 5 $0.00042 $0.00428
Sonnet 5 $0.00017 $0.00171
Haiku 4.5 $0.00008 $0.00086

Measured 2d ago against content hash e56ab56fdaf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/fleet/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/foundry:fleet

The operator's single-pane view for supervising many parallel sessions (the cognitive-load surface). A thin overlay over native Claude Code session machinery — it does NOT rebuild what the harness ships (claude agents already enumerates sessions + their needs-input state + a summary). Foundry adds the one thing native cannot know: each session's work-context — which release/feature/atom it serves, its governance state, and any operator-reported why/pending-decision/blocker.

What it shows

scripts/foundry-fleet-roster.py renders one row per native session (via the session-registry):

  • native base (harness-authoritative): session id, repo (cwd), branch, name, state, a best-effort liveness value (native updated_at, "—" when absent — no fabricated "live", no dead-PID stale flag);
  • foundry overlay: epic/atom, governance state, a pending-decision marker;
  • headline machinery scan columns (joined from the session-machinery overlay by session_id): ISO (isolation), GATE (gate/merge-readiness), WF·step (workflow+stage). These are DEFAULT-DENY: a value renders clear only when it is in that field's explicit known-safe set (e.g. GATE clear only for a derived authorized/gate_pass/merged; ISO clear only for worktree); every other value — unknown, gate_block, direct_main, worktree_on_main, a null/un-derived risk value, or any novel/out-of-vocabulary token — renders (attention), never blank-as-green. A row whose machinery block is entirely missing renders ⚠ machinery unavailable. WF·step is honestly sparse — the workflow pointer is the invoking session's own, so it shows for that row and "—" for others. The fuller machinery (mode, security-flag, infra blast radius, target-repo) is drilldown in --json;
  • a one-line summary = the native Haiku summary suffixed with the foundry atom/step.

It is read-only (renders, never acts; runs in any session — operator or worker — with no dispatch queue, worktree, or special mode, and never trips worker-cwd-enforcement), secret-scrubbed + sanitized on EVERY rendered string (the native summary/name/branch are session-content-derived → the security-review floor; C0 and C1 control ranges + ANSI), fail-closed (if the native list can't be read it shows a visible banner, never an empty "all clear"), and --json for scripting.

Read the full file on GitHub · 47 lines

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.

  1. 2d ago First seen · 47 lines · 83 tokens per session scan A e56ab56fdaf1

Subscribe to this mod's changes

fleet is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 856 once invoked, about $0.0004 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 2026-08-31.