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/kelp/agent-plugins/fleet-leadnpx skills add kelp/agent-plugins --skill fleet-leadgit clone --depth 1 https://github.com/kelp/agent-pluginsWhat 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 | $0.00093 | $0.01580 |
| Opus 5 | $0.00046 | $0.00790 |
| Sonnet 5 | $0.00019 | $0.00316 |
| Haiku 4.5 | $0.00009 | $0.00158 |
Grade A, and why
fleet-lead 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Lead (two leads, one ledger)
Two long-lived sessions run several work units against one repo. The leads do not write code. They claim work, hold the gates, and delegate every change to the project's pipelines.
This is the operating procedure for the sessions above the fleet.
For the token rules inside a fan-out, read the sibling
fleet-efficiency skill before dispatching three or more agents.
When to use
Use it to start a fleet, to join one as the second lead, to claim or release a unit, or when a unit stops reporting.
Do not use it for one unit. A single change goes straight to the project's pipeline; a fleet around it is pure overhead.
Why two leads
Only a main loop can sign a commit. Subagents inside a workflow cannot, so every unit returns to a session to commit.
A session waiting at that gate looks exactly like a session doing work. Signing agents drop: an SSH key held by a password manager loses its host connection after sleep or a reconnect, and the commit hangs until a human refreshes the session. The gate lead exists to notice, because nothing else does.
Restarting is the second reason. A lead that dies takes its context with it, and a fleet with no second lead stalls until the human looks.
Roles
Drive lead (lead-drive): picks units, claims them in the
ledger, dispatches the pipelines, signs the commits, opens the
pull requests. The only writer of the ledger.
Gate lead (lead-gate): watches CI, drains review threads,
runs the cross-platform checks, reads heartbeats, restarts a dead
unit. Never writes the ledger; sends what it wants changed to
lead-drive over SendMessage.
Two writers on one ledger is the failure this split prevents. Keep the single-writer rule even when the drive lead is busy.
Names
Names are SendMessage addresses. Keep them stable across a restart, so a ledger row still points at a live agent.
- Leads:
lead-drive,lead-gate. - Unit owning one component:
unit-<component>. - Unit owning shared code:
unit-common-<topic>.
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 · 161 lines · 0 tokens per session scan A 1d65f6223fa8
fleet-lead is a skill published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 93 tokens to every session and 1,580 once invoked, about $0.0005 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
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…
competitive-battlecard
Create sales-ready competitive battlecards comparing your product against a specific competitor — positioning, feature comparison, objection handling, and win/loss patterns. Use when preparing sales teams, creating competitive materials, or responding to 'why not competitor X?'.