New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Fleet Manager

by dreamers-laboratory in dreamers-laboratory/agent-fleet-manager

Operate an agentfleet fleet for large-scale periodic information gathering.

Apache-2.0Auto-check passedDevOps & Cloud

Install Agent Fleet Manager

skills CLI
$ npx skills add dreamers-laboratory/agent-fleet-manager --skill agent-fleet-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dreamers-laboratory/agent-fleet-manager agent-fleet-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-fleet-manager
GitHub stars
147
Token cost
~928 tokens
SKILL.md length
425 words
Files
16
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Operate an agentfleet fleet for large-scale periodic information gathering.

  • Works in 5 steps: In Python: manifest =… → For each batch in the manifest, for each… → Write {action_id}.json into that batch's… → …
  • The user wants to monitor many sources on a schedule (prospect signals
  • SKILL.md covers Register what to watch, Run a sweep, Act as a worker yourself and Optional Jev evaluation, plus 2 more sections
  • Runs Python scripts from its folder; calls python; needs TYPESAFE_API_KEY

What it does

Agent Fleet Manager is an agent skill from dreamers-laboratory/agent-fleet-manager. Operate an agentfleet fleet for large-scale periodic information gathering. Use when the user wants to monitor many sources on a schedule (prospect signals, competitor pages, regulatory updates, listings, datasets), act as a worker executing leased batches, review what changed or failed across the fleet, or export fleet activity as OpenTelemetry traces.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files (for example `CHANGELOG.md`, `README.md` and `agentfleet/__init__.py`).

It sits in DevOps & Cloud, covering Observability and Competitor analysis. It works with OpenTelemetry. The repository describes itself as: A general-purpose engine for large-scale, repeated information gathering by a fleet of workers. The licence is Apache-2.0.

When your agent uses it

  • The user wants to monitor many sources on a schedule (prospect signals
  • Competitor pages
  • Regulatory updates
  • Act as a worker executing leased batches

Example prompts

  • “/agent-fleet-manager”

Requirements

  • Python 3
  • A credential in TYPESAFE_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. In Python: manifest = agentfleet.lease(conn, scope_root).
  2. For each batch in the manifest, for each action: perform the check however the route demands. Compute sha256 and byte count of the content…
  3. Write {action_id}.json into that batch's write_scope with: action_id, source_id, status ("ok" or an error string), sha256, bytes…
  4. Write nothing anywhere else. The write scope is the entire surface a worker may touch.
  5. agentfleet.reconcile(conn, batch_id).

What it can do on your machine

Read from SKILL.md and the folder at commit 31261ed. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • TYPESAFE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Fleet Manager loads about 928 tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 425 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~928

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dreamers-laboratory/agent-fleet-manager at commit 31261ed, republished under its Apache-2.0 licence (© dreamers-laboratory). 425 words, ~928 tokens.

Download SKILL.mdSave it as .claude/skills/agent-fleet-manager/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
agent-fleet-manager
description
Operate an agentfleet fleet for large-scale periodic information gathering. Use when the user wants to monitor many sources on a schedule (prospect signals, competitor pages, regulatory updates, listings, datasets), act as a worker executing leased batches, review what changed or failed across the fleet, or export fleet activity as OpenTelemetry traces.

Operating an agentfleet fleet

One SQLite file holds the whole fleet. All commands take --db <path>. Full mechanics are in README.md; this file is the operating procedure.

Register what to watch

python -m agentfleet.cli add-source --db fleet.db <name> <route> --cadence <seconds>

The route means whatever your worker decides: a URL for the built-in HTTP fetcher, a search query, an API endpoint, a natural-language instruction for an agent worker. Pick cadences honestly — a careers page is an hourly-to-daily source; a statute database is weekly. Do not register sources the user has no right to fetch, and respect robots.txt and rate expectations when the worker is a fetcher you control.

Run a sweep

python -m agentfleet.cli sweep --db fleet.db --scopes ./scopes

Queues everything due, leases batches, fetches over HTTP, reconciles. Nothing due means the sweep is a cheap no-op, so running it on a timer is fine.

Act as a worker yourself

When routes need judgment (log in, interpret a page, summarize a diff), be the worker instead of the HTTP fetcher:

  1. In Python: manifest = agentfleet.lease(conn, scope_root).
  2. For each batch in the manifest, for each action: perform the check however the route demands. Compute sha256 and byte count of the content you retrieved.
  3. Write {action_id}.json into that batch's write_scope with: action_id, source_id, status ("ok" or an error string), sha256, bytes, started_at, finished_at (UTC, %Y-%m-%dT%H:%M:%SZ), elapsed_ms. Optionally write the payload beside it.
  4. Write nothing anywhere else. The write scope is the entire surface a worker may touch.
  5. agentfleet.reconcile(conn, batch_id).

Skipping a result file marks that action failed; the engine requeues and backs off on its own. Never edit the source, action, or observation tables directly — reconcile is the only door into canonical state.

Show full SKILL.md (158 more words)Show less

Optional Jev evaluation

Only with authorized data sharing: use jev-evaluate <request.json> for explicit state/questions, or sweep --jev-questions <questions.json> to send fetched UTF-8 text to the official TypeSafe API. Set TYPESAFE_API_KEY in the environment; never store it in routes, inputs, receipts or Git. See README.md for examples. Preserve ambiguous cases for review; a model answer is not an automatic approval/rejection. API failures are failed checks, not negative findings. Answers, usage and phase timings live in receipts; source hashes remain unchanged.

Review the fleet

python -m agentfleet.cli status --db fleet.db   # per-source: next due, checks, changes, error streak
python -m agentfleet.cli stats  --db fleet.db   # change %, error %, median/p95 latency, fleet totals

When reporting to the user, lead with what changed (the point of the fleet), then what is failing and how far it has backed off. A source with a growing error streak needs a route fix or removal; say so rather than letting it back off forever.

Export telemetry

python -m agentfleet.cli export-otel --db fleet.db --endpoint <otlp-http-collector>

Run → trace, batch → parent span, action → child span. Use it when the user has Grafana or any OTLP collector; omit --endpoint to inspect JSON on stdout first.

© dreamers-laboratory, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 15 other files in the repository root of dreamers-laboratory/agent-fleet-manager.

  • SKILL.md
  • .gitignore
  • CHANGELOG.md
  • LICENSE
  • README.md
  • agentfleet/__init__.py
  • agentfleet/cli.py
  • agentfleet/engine.py
  • agentfleet/jev.py
  • agentfleet/otel.py
  • agentfleet/schema.sql
  • examples/demo.py
  • examples/jev_questions.json
  • examples/jev_request.json
  • tests/test_engine.py
  • tests/test_jev.py

Open the folder on GitHubat commit 31261ed

Compare with similar skills

Agent Fleet Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Fleet Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Fleet Manager this skilldreamers-laboratory/agent-fleet-manager147—~928Automated safety check: PassApache-2.0
Motel Debugkitlangton/motel298—~2.2kAutomated safety check: PassMIT
Tempsgotempsh/temps833—~2kAutomated safety check: PassApache-2.0
Axiom Metrics Queryopenclaw/clawhub9.5k—~2.6kAutomated safety check: PassMIT
UModel Root Cause Analysisalibaba/UnifiedModel415—~1.9kAutomated safety check: PassCustom licence
Agent Kill Switchvivekchand/clawmetry426—~1.1kAutomated safety check: PassMIT

Similar skills

  • Motel Debug

    kitlangton/motel

    Debug applications with motel, a local OpenTelemetry ingest and query server.

    298 GitHub stars~2.2k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

  • Temps

    gotempsh/temps

    Manage, deploy, operate, and instrument applications with Temps.

    833 GitHub stars~2k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Axiom Metrics Query

    openclaw/clawhub

    Explores and queries OpenTelemetry metrics in Axiom MetricsDB, listing datasets, metrics and tags first and picking the right aggregation for each metric's type.

    9.5k GitHub stars~2.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • UModel Root Cause Analysis

    alibaba/UnifiedModel

    Investigates a service incident to its root cause by querying a UModel object graph alongside metrics, logs, topology and recent deployments.

    415 GitHub stars~1.9k tokensUpdated 17 days ago
    DevOps & CloudAuto-check passed

  • Agent Kill Switch

    vivekchand/clawmetry

    Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.

    426 GitHub stars~1.1k tokensUpdated 3 days ago
    DevOps & CloudAuto-check passed

  • Agentmeasure

    roy-tong/AgentMeasure

    Check whether agent telemetry preserves measurement semantics.

    219 GitHub stars~753 tokensUpdated today
    DevOps & CloudAuto-check passed

Works with

Categories

Questions about Agent Fleet Manager

What does Agent Fleet Manager do?

Operate an agentfleet fleet for large-scale periodic information gathering. Agent Fleet Manager is an agent skill from dreamers-laboratory/agent-fleet-manager. Operate an agentfleet fleet for large-scale periodic information gathering.

When should I use Agent Fleet Manager?

Agent Fleet Manager fits situations like: the user wants to monitor many sources on a schedule (prospect signals; competitor pages; regulatory updates; act as a worker executing leased batches.

How do I install Agent Fleet Manager in Claude Code?

Run `npx skills add dreamers-laboratory/agent-fleet-manager --skill agent-fleet-manager -a claude-code`. Or copy the skill folder (the dreamers-laboratory/agent-fleet-manager repository) into .claude/skills/agent-fleet-manager in your project. Claude Code loads it when a task matches its description.

How do I install Agent Fleet Manager in Codex?

Run `npx skills add dreamers-laboratory/agent-fleet-manager --skill agent-fleet-manager -a codex`. Or copy the skill folder (the dreamers-laboratory/agent-fleet-manager repository) into .agents/skills/agent-fleet-manager in your project. Codex loads it when a task matches its description.

Can I use Agent Fleet Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dreamers-laboratory/agent-fleet-manager --skill agent-fleet-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-fleet-manager, .gemini/skills/agent-fleet-manager, .github/skills/agent-fleet-manager and .opencode/skills/agent-fleet-manager in your project.

What does Agent Fleet Manager need to run?

Going by SKILL.md and its folder, Agent Fleet Manager needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named TYPESAFE_API_KEY. Our summary lists: Python 3; A credential in TYPESAFE_API_KEY.

Does Agent Fleet Manager access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Fleet Manager safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Fleet Manager use?

Agent Fleet Manager is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Fleet Manager use?

About 928 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Fleet Manager?

Skills that share tags, products or a category with Agent Fleet Manager: Motel Debug (kitlangton/motel, 298 stars), Temps (gotempsh/temps, 833 stars), Axiom Metrics Query (openclaw/clawhub, 9.5k stars) and UModel Root Cause Analysis (alibaba/UnifiedModel, 415 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Fleet Manager?

dreamers-laboratory (a GitHub organization) maintains it in dreamers-laboratory/agent-fleet-manager, which has 147 GitHub stars. The repository was last updated on October 1, 2026.

Source: dreamers-laboratory/agent-fleet-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.