Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/datacore-one/datacorenpx agentmods add commands/datacore-one/datacore/fleet-simWrote 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/commands/datacore-one/datacore/fleet-sim)<a href="https://agentmods.dev/commands/datacore-one/datacore/fleet-sim"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/fleet-sim/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/commands/datacore-one/datacore/fleet-sim"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/fleet-sim.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 | $0.00032 | $0.01086 |
| Opus 5.5 | $0.00013 | $0.00434 |
| Sonnet 5.5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
fleet-sim 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 13d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fleet-sim
Run a simulated week of the whole fleet's real schedule in a sealed Linux container on the Mac, and list what breaks — then say what changed since the last run. Issue datacore-one/datacore #222.
Usage
/fleet-sim # 7 simulated nights (about an hour)
/fleet-sim 2 # 2 nights (quick check after a fix)
/fleet-sim selftest # the simulator's own tests, in the container (about ten minutes)
/fleet-sim harsh # 7 nights with the harsh faults on top (F13-F25), compressed to 2-hour steps
harsh adds the faults of HARSH_FAULTS in fleet_week_sim.py to F1-F12, several
at once: network throttling and loss (real tc netem on the container's
loopback plus the stand-ins), partitions between pairs of machines, a machine
down for hours mid-job, repeated reboots, out of memory mid-task (the process,
and the whole run), a full disk, clock skew, GitHub unreachable, a rotated
credential on one machine, a second writer in the overnight host's checkout,
a slow and a rate-limited model. Run it as
python3 .datacore/lib/fleet_week_sim.py docker --days 7 --harsh --min-interval 7200
(about two hours). The report opens with what the owner would have had each
night: was the delegated task completed, did the briefing and its audio go out.
Not scheduled. The owner decides a cadence later; run it by hand.
Steps
-
Pre-flight. On the Mac only (it needs Docker). Check
docker infoanswers. If Docker is not running, say so and stop — do not try another machine. The simulator reads committed files (git HEAD) plus five gitignored config files; say if the working tree has uncommitted product changes, because those are NOT in the run. -
Run. From the install root, in the background (it takes 50–75 min for 7 nights):
python3 .datacore/lib/fleet_week_sim.py docker --days NNis the argument, default 7. Forselftest:python3 .datacore/lib/fleet_week_sim.py docker --selftest(no report, no compare).
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.
- 13d ago Changed · +13 lines e3cd0900a31e
- 15d ago First seen · 77 lines · 32 tokens per session scan A b02f040d3fc3
fleet-sim is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,086 once invoked, about $0.0001 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 2026-10-01.
Other commands, from other repositories
plan-sdd
A command that creates an implementation plan from a written specification using Clean Architecture and TDD. TDD, or test-driven development, means writing tests before the code they check.
test-browser
Run browser tests on pages affected by current PR or branch.
xcode-test
Build and test iOS apps on simulator using XcodeBuildMCP.
compress
Save this Claude Code session to the vault and update the semantic memory index.
checkpoint
Save a mid-session checkpoint — for continuity between sessions of the same day.
voice-refresh
Refresh the founder-voice DNA from new Granola meetings (interactive, MCP-backed). Pulls meetings since the last refresh, harvests Assaf-only speech, runs the Stage 2-3 orchestrator, and presents a founder-gated delta. Never auto-writes voice-dna.md.