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.
git clone --depth 1 https://github.com/eai-support/eai-goferWrote 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/eai-support/eai-gofer/eai-update)<a href="https://agentmods.dev/commands/eai-support/eai-gofer/eai-update"><img src="https://agentmods.dev/badge/commands/eai-support/eai-gofer/eai-update/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/eai-support/eai-gofer/eai-update"><img src="https://agentmods.dev/badge/commands/eai-support/eai-gofer/eai-update.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 | $0.00000 | $0.01315 |
| Opus 5.5 | $0.00000 | $0.00526 |
| Sonnet 5.5 | $0.00000 | $0.00263 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
eai-update 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update EAI Gofer
Use this command to install or update EAI Gofer for the current AI coding app. This command works without an EAI project, a Gofer scaffold, or EAI sign-in.
Update Contract
- Do not run workspace checks,
eai init,eai whoami, or pipeline stages. - Use
claudeas the current semantic host. - Check the current host first:
node <plugin-root>/.specify/scripts/node/gofer-surface-update.mjs --action inspect --host claude --json - If the plugin root is not known, identify the installed plugin bundle before you run the helper.
- State whether EAI Gofer is installed and whether the host command is available.
- Explain the planned user-level change and ask for approval before any install or update command.
- After approval, run one of these commands from the bundled helper:
- Install:
node <plugin-root>/.specify/scripts/node/gofer-surface-update.mjs --action install --host claude --execute --json - Update:
node <plugin-root>/.specify/scripts/node/gofer-surface-update.mjs --action update --host claude --execute --json
- Install:
- After an actual install or update, the helper archives stale Gofer command and skill entries. It adds a small managed always-on instruction for Claude, Codex, Copilot, Antigravity, and VS Code. For Grok, it verifies the installed plugin's
skills/eai/SKILL.mdalways-on contract instead of inventing a separate global instruction file. It keeps the currenteaiandeai-updateentries. For Codex, a clean official local marketplace onmainfast-forwards safely. A dirty, non-main, or unrecognised local marketplace remains unchanged and reports that its plugin update is incomplete while it still refreshes the always-on instruction. If the Codex marketplace source is unknown, it stops without changes. - Run only the selected host by default. Use
--host allonly when the user explicitly asks to install or update every detected host. - Show the required reload step from the helper output. Do not claim the command is ready until the host reloads.
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.
- 1mo ago Changed · +2 lines 7a7bba0764f4
- 1mo ago Changed · +1 lines 830863b95eb6
- 1mo ago Changed · +10 lines 83a02f43d1ac
- 1mo ago Changed d2a99d67f0ca
- 1mo ago First seen · 34 lines · 0 tokens per session scan A ba11df14ef91
eai-update is a command published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,315 tokens. 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 2026-09-03.
Other commands, from other repositories
ship
Run the Android pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision with rollback and staged rollout plan.
code-simplify
Simplify code incrementally while preserving behavior exactly.
brainstorm
A retired command for generating ideas before implementation. Its description says to use the Superpowers brainstorming skill instead.
execute-plan
A deprecated command that tells users to use the corresponding plan-execution skill instead.
test
Write tests before implementation using Red-Green-Refactor.
adr-review
Run the workflow in docs/playbooks/adr-review.md. You review only — never write or rewrite the ADR for me. Check problem framing, option fairness, trade-offs and consequences, reversibility, the revisit trigger, and weak reasoning. Give pointed questions and concrete suggestions; I write the words. If it supersedes an…