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 skills/lukasrepublic/agentic-foundry/fleetnpx skills add lukasrepublic/agentic-foundry --skill fleetgit clone --depth 1 https://github.com/lukasrepublic/agentic-foundryWhat 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 | $0.00083 | $0.00856 |
| Opus 5 | $0.00042 | $0.00428 |
| Sonnet 5 | $0.00017 | $0.00171 |
| Haiku 4.5 | $0.00008 | $0.00086 |
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.
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-machineryoverlay bysession_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.GATEclear only for a derivedauthorized/gate_pass/merged;ISOclear only forworktree); 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·stepis 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.
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 · 47 lines · 83 tokens per session scan A e56ab56fdaf1
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.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.