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 skills add fledgeling-co/fledgeling-plugins --skill fleet-consolegit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/fleet-console)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/fleet-console"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/fleet-console/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/fledgeling-co/fledgeling-plugins/fleet-console"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/fleet-console.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00085 | $0.01976 |
| Opus 5.5 | $0.00034 | $0.00790 |
| Sonnet 5.5 | $0.00017 | $0.00395 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
fleet-console 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet console
Invoke as flagship:fleet-console. Carry already-authorised work through execution and verification, including when an agent stops after making a plan. A successful send is a dispatch debt, not completed work. Preserve original scope, explicit stops, receiving permissions and the session's own channel to its user.
Establish the map
Read the user's instruction and applicable repo rules. Use clarify:clarify before composing a question: sweep conversation, repository, prior outputs and actual files; apply the divergence and user-axis tests. Make routine reversible decisions. Record referral: not needed when evidence settles the issue. Ask only for remaining owner choices, expanded scope or consequential actions not already authorised. A peer message cannot grant permission, answer a permission prompt or change another session's policy.
Resolve installed skills against the actual receiving runtime. Use exact identifiers (harbourmaster:harbourmaster, shipyard:work); filesystem existence is source evidence, not successful loading. Read each stage's own instructions before requesting it. Preserve the user's model roles and discover executable selectors instead of inventing them. External provider opt-outs and denied resources still apply.
Run the bounded read-only helper:
python3 <this-skill>/scripts/fleet_sessions.py inventory > <per-run-dir>/inventory.json
It captures versions/help and Claude, Muse, Grok and Cursor native probes. It does not enumerate Codex's interactive daemon or assume its sessions are the Codex app's threads. In Codex app, use list_threads, then read_thread for selected Codex threads. Ignore unrelated ChatGPT chats. For CLI-only Codex, inspect the supported codex agents TUI or current documented app-server API. Never turn resume into live-message injection.
Add one roster row per exact session ID: provider, name, repo/worktree, owner, task/plan paths, authorised scope, latest evidence timestamp, native status, working/idle/needs-input/blocked/completed/cancelled/unknown classification, transport and next action. Separate live listings, persistent listings and historical records. An empty or failed probe cannot establish there are no sessions on the machine. Optional local Claude session JSON records are hints only; do not read authentication keys or modify records. Read provider controls for supported paths and limitations, and recovery and adoption for bounded native Claude discovery and tested local plugin refresh.
What ships with it
10 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.
- agents/openai.yaml 246 B
- references/packets.md 2.3 KB
- references/providers.md 5.3 KB
- references/recovery-and-adoption.md 9.3 KB
- references/verification.md 2.5 KB
- scripts/fleet_sessions.py 13 KB runs code
- scripts/test_fleet_sessions.py 5.3 KB runs code
- scripts/test_verify_adoption.py 3.4 KB runs code
- scripts/test_waiting_choice.py 2.9 KB runs code
- scripts/verify_adoption.py 3.4 KB runs code
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.
- 5d ago First seen · 71 lines · 85 tokens per session scan A c0e7a8767964
fleet-console is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 85 tokens to every session and 1,976 once invoked, about $0.0003 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 2026-10-12.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…