Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add andreymudri/claude-teammates/plugin install claude-teammatesWrote 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/andreymudri/claude-teammates/fleet-lifecycle)<a href="https://agentmods.dev/skills/andreymudri/claude-teammates/fleet-lifecycle"><img src="https://agentmods.dev/badge/skills/andreymudri/claude-teammates/fleet-lifecycle/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/andreymudri/claude-teammates/fleet-lifecycle"><img src="https://agentmods.dev/badge/skills/andreymudri/claude-teammates/fleet-lifecycle.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 | $0.00025 | $0.01545 |
| Opus 5 | $0.00013 | $0.00772 |
| Sonnet 5 | $0.00005 | $0.00309 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
fleet-lifecycle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fleet Lifecycle
When the run directory is gone
.teammates/ is gitignored, so a clean checkout or a stray delete takes a run's bookkeeping with
it. Rebuild it from git rather than hand-writing JSON:
node "$CLAUDE_PLUGIN_ROOT/scripts/cli.mjs" rebuild-state --run <runId> --plan <planPath> --root <project root>
It derives every task's state from its branch — merged or contributing is done, a branch that
exists and contributes nothing is orphaned, no branch is pending — and refuses to overwrite
state that still exists unless you pass --force. It reconstructs no gate history: a verdict
is evidence that checks ran, and git carries branches, not evidence. Every phase of a rebuilt run
has to be gated again before anything is reported done.
Map notes
For what a target project's modules are for — the part git statistics cannot supply — a run may carry hand-written notes on it, verified and refreshed with:
node "$CLAUDE_PLUGIN_ROOT/scripts/cli.mjs" map-notes --run <runId> --root <project root>
Exit 0 means the stored notes declare the commit the repository is on; the header is a string the
writing agent was told to copy, so this is tamper-evident provenance and not proof — nothing
observes which tree that agent actually read, and nothing detects a header edited afterwards.
Exit 4 means there are none, they carry no header at all, they name a different commit, they were
written for a different run, or the file could not be read, and it prints the exact prompt to
dispatch. Exit 2 means git could not be read, so no comparison happened at all — read that as
unknown, never as current. Dispatch a read-only agent with the printed prompt; it RETURNS the map
and you write it to that path yourself, with the same command and --write:
node "$CLAUDE_PLUGIN_ROOT/scripts/cli.mjs" map-notes --run <runId> --root <project root> --write <path to the agent's returned text>
That reads the returned text from <path>, checks the same header plus a body check — text must
remain once the header is stripped off, so an agent that echoes back only the line it was handed
writes nothing — and only then writes it to the notes file: it exits 0 on a write and exits 2 if
--write is given no path. Exit 4 covers every way that read, that validation, or the write
itself can fail — nothing is written in any of those cases, and the printed message names the
reason, so read the message rather than parsing the exit code alone. A teammate
never writes this file, and nothing enforced ever reads it. The directory names that
prompt carries are filtered — anything that is not a plain path segment is dropped — because that
prompt is handed to an agent that has Bash and is gated by nothing.
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.
- 9d ago First seen · 119 lines · 25 tokens per session scan A 13dc385c42a1
fleet-lifecycle is a skill published in the GitHub repository andreymudri/claude-teammates (2 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 1,545 once invoked, about $0.0001 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-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
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.
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…