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 teranos/ground --skill ground-commandsgit clone --depth 1 https://github.com/teranos/groundWrote 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/teranos/ground/ground-commands)<a href="https://agentmods.dev/skills/teranos/ground/ground-commands"><img src="https://agentmods.dev/badge/skills/teranos/ground/ground-commands/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/teranos/ground/ground-commands"><img src="https://agentmods.dev/badge/skills/teranos/ground/ground-commands.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 | $0.00023 | $0.00394 |
| Opus 5.5 | $0.00009 | $0.00158 |
| Sonnet 5.5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
ground-commands 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 12d 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.
What it actually says
# run by Claude Code on every hook event, the event's JSON on stdin:
ground < event.json
# search past hook events by wildcard pattern
# (see: ground events)
ground shovel PostToolUse "*pr create*"
# or dump a session's transcript:
ground shovel session ses90l3m
# post the pbt's attestations to their backends (make install does):
ground attest
# timing table:
ground profile
# one event, its phases and its worst runs:
ground profile PreToolUse
# the courier, with "timeout": 86400 on its hook entry
ground sky $PWD
# perform a ritual, by its name when that names one:
ground ritual grove
# or by project and ritual when it does not:
ground ritual q.sbvh.nl boxsurvival
# end a live performance, by its ritual or by the handle on the status line:
ground abort grove
# the driver ground ritual forks, one per performance, by the performance id:
ground drive ground-coinflip-1786812152
# run by the script that starts a ritual's agent, what `claude --bg` printed on stdin:
ground bind ground-coinflip-1786812152 < started.txt
# every hook event ground answers to:
ground events
# set a .pbt in the one layout, or the pbt fixtures in a .d:
ground fmt controls/controls.pbt
ground fmt source/proto_test.d
# the author's tool, in the ground checkout: every case editable in a browser
ground author
# how much of each rate limit is used, and how the week got there:
ground usage
# strip the bulk out of the db (make install does):
ground decay
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.
- 12d ago Changed 1c7e04773a15
- 20d ago Changed · +3 lines 38e5da9cefec
- 23d ago Changed · +6 lines 4d40e4082647
- 25d ago First seen · 48 lines · 23 tokens per session scan A 15ddd762cc58
ground-commands is a skill published in the GitHub repository teranos/ground (2 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 394 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 2026-09-14.
Other skills, from other repositories
jobs
Manage agy staffer background jobs - collect results, check status, cancel, follow-up conversation, and setup. Use when an agy job needs collecting, when the user asks "is the agy job done", "show agy's result", "cancel the agy job", "continue the agy conversation", or "set up agy". This is the orchestrator's skill…
party
Throw or join an agents-party: a shared channel where several AI agent sessions (and their humans) talk to each other — Claude Code, Cursor, Codex or any other agent, on one machine or across machines. Use when the user asks to throw or start a party, wants several agent sessions to collaborate in one chat, wants two…
generate-daily-schedule
Use when turning a day's structured inputs — fixed commitments, tasks, and free windows — into a concrete 15-minute schedule. Domain-agnostic; the caller provides all context.
agy-jobs
Manage agy staffer background jobs - collect results, check status, cancel, follow-up conversation, and setup. Use when an agy job needs collecting, when the user asks "is the agy job done", "show agy's result", "cancel the agy job", "continue the agy conversation", or "set up agy". This is the orchestrator's skill…
mode-interactive
The interactive implementation posture (/foundry:mode-interactive) — the default lean direct loop. The operator drives edit→verify→merge in one accountable context; the operator reviews the diff at the merge button (the Regular-mode segregation). Sibling of mode-autonomous; they differ ONLY at the two ends (who paces…
token-efficiency
Token conservation economics, bounded context-window pruning, AST structural query optimization, and high-precision prompt budget discipline.