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/jasonsuhari/gridbash/gridbash-panesnpx skills add jasonsuhari/gridbash --skill gridbash-panesgit clone --depth 1 https://github.com/jasonsuhari/gridbashWhat 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 | $0.00097 | $0.01523 |
| Opus 5 | $0.00048 | $0.00762 |
| Sonnet 5 | $0.00019 | $0.00305 |
| Haiku 4.5 | $0.00010 | $0.00152 |
Grade A, and why
gridbash-panes 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GridBash pane coordination
You are one pane in a GridBash grid. Other panes are independent coding agents working in the same repository, often in separate worktrees. GridBash exposes a localhost control API so panes can see and talk to each other.
First: are you actually in a GridBash pane?
Check for GRIDBASH_CONTROL_ADDR. If it is unset, you are not in a GridBash
pane and none of this applies — say so instead of guessing.
Panes inherit GRIDBASH_CONTROL_ADDR, GRIDBASH_CONTROL_TOKEN,
GRIDBASH_CONTROL_SESSION, GRIDBASH_PANE_INDEX (1-based, changes on reorder),
and GRIDBASH_PANE_ID (stable). The CLI reads all of these itself — never pass
--session or --token from inside a pane.
The two surfaces
Both reach the same API. Use whichever your harness makes cheaper.
CLI — always available in a pane, zero setup:
gridbash agent panes
gridbash agent prompt --pane pane-4-gen-2 "Rebase onto main, then report"
printf "Report status, blockers, and next action" | gridbash agent prompt --others
gridbash agent rename "Reviewer"
gridbash agent rename --pane pane-4-gen-2 --clear
MCP — richer output, requires the client to be pointed at gridbash --mcp:
| Tool | Use it for |
|---|---|
gridbash_get_grid_snapshot |
Who exists, their role, state, and a one-line activity summary |
gridbash_read_pane_output |
Bounded recent output from specific stable pane IDs |
gridbash_prompt_panes |
Prompt explicit targets, or other_panes: true for everyone else |
gridbash_rename_pane |
Set or clear a pane title |
gridbash_send_command |
Raw shell text into a pane (not an agent prompt) |
gridbash_set_status |
One-line message in the grid status bar |
gridbash_capture_output / gridbash_start_logging / gridbash_stop_logging |
Persist pane output to files |
Pane targets
Snapshots return two identifiers per pane. Use the right one:
target(pane-4-gen-2) — stable. Survives reordering, and fails loudly if the pane was replaced. Use this for anything that writes to a pane.pane_number(1-based) — display position only. It shifts when panes move.
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 · 141 lines · 97 tokens per session scan A 45f62a353bdb
gridbash-panes is a skill published in the GitHub repository jasonsuhari/gridbash (131 stars, last pushed 2d ago), licensed MIT. It adds 97 tokens to every session and 1,523 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 2026-08-30.
Other skills, from other repositories
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
setup-omnara-agent
Install and set up Omnara. Use when the user asks to install Omnara or run /setup-omnara-agent.
openpets
Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.
helmor-cli
Use the Helmor CLI to remote-control Helmor from the terminal. Use when the user asks to inspect Helmor data/settings, manage repositories/workspaces/sessions/files, send prompts to agents, list models, use GitHub integration, inspect scripts, run Helmor as an MCP server, generate shell completions, quit a running…
onboard-repository
Inspect an unfamiliar or brownfield repository, trace one real operational path, and propose evidence-backed improvements that help future agents work independently. Use when explicitly asked to onboard, map, assess, or backfill agent-facing repository guidance; use again after the user approves exact proposal items.…
improve-harness
Run one explicitly authorized, evidence-backed improvement to a repository's agent guidance, tools, runbooks, or validation. Use only when the user invokes $improve-harness or explicitly asks to improve the Harness after observed reusable agent friction. Do not use for ordinary product changes, speculative cleanup…