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/eai-support/eai-gofernpx agentmods add commands/eai-support/eai-gofer/0_gofer_startWrote 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/0_gofer_start)<a href="https://agentmods.dev/commands/eai-support/eai-gofer/0_gofer_start"><img src="https://agentmods.dev/badge/commands/eai-support/eai-gofer/0_gofer_start.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.18306 |
| Opus 5 | $0.00010 | $0.09153 |
| Sonnet 5 | $0.00004 | $0.03661 |
| Haiku 4.5 | $0.00002 | $0.01831 |
Grade A, and why
0_gofer_start 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 today.
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 — 1,589 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Start Gofer, confirm EAI readiness, and orchestrate the unified pipeline
Gofer Start
Continuation And Stop Contract
- Preserve the requested scope and mode, including read-only, plan-only, research-only and MVP work. Keep the full applicable pipeline, stage functions, artifacts, reviews and validation; do not expand an MVP into an unapproved release.
- After a stage's required evidence is complete, read and follow the next internal file in .specify/commands/ in the same conversation. Do not require a numbered command or a host-specific skill dispatcher. Optional helpers remain optional; maintenance and control commands do not start delivery work.
- After explicit business-specification approval, continue routine planning, tasks, implementation and validation within that approved scope. Record the approval source and scope; missing or ambiguous approval is not approval. A proposal or generated status is not user consent.
- Preserve any explicit plan/task approval requirement unless it is already satisfied by recorded user approval covering that work. Rejected, revoked, changed or unclear approval requires a pause. Never invent approvedBy, approvedAt or a new approval event when reusing an existing approval.
- Pause for material scope, security, cost, deployment, destructive or protected files/boundary changes and any outstanding user gate. Business approval does not authorize publishing, spending, external changes or bypassing host permissions. Complete safe authorized work without bypassing the blocked gate.
- A tool proposal is not execution. If host consent is required, wait for it. After the tool result or approved proposal returns, inspect the result and resume the next authorized action within approved scope; do not end with only a plan or a proposed tool call. A denied tool or unavailable capability must not be bypassed through another host or CLI.
- Use the current agent's available native tools. Optional Gofer/MCP tools are conveniences, not prerequisites. If the current agent lacks a required capability, report that limitation and the safe next action; do not pretend a handoff button transfers control automatically.
- Stop after research only when research-only work was requested, the user paused, or a real gate blocks progress. Otherwise continue to specification. At validation, report completion only when the requested scope's required evidence passes; failures remain unfinished work.
- Respect budget, context and retry limits from the existing loop contract. Repair safe within-scope failures only within those limits. Preserve a checkpoint before an orderly context stop; resume by reading its recorded stage and rechecking scope, approvals and evidence. Never claim an abrupt host termination was handled.
- Report concise Progress during work. At every controlled stop, report Progress, Stop reason and Next action, including the exact missing input or approval and unfinished work. Reasons are requested scope complete, user pause, approval required, material change, missing capability/access, validation blocked, or budget/context/retry limit. Stage completion alone is not pipeline completion.
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.
- today Changed · +18 lines de0b040b2cfa
- 7d ago First seen · 1,571 lines · 20 tokens per session scan A d4c99bed2401
0_gofer_start is a command published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 18,306 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 commands, from other repositories
aivo_guide
Command "aivo_guide" from yuanchuan/aivo, covering aivo — complete usage guide, global usage, providers & keys — aivo keys, account — aivo account and models & aliases.
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.
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.
test
Write tests before implementation using Red-Green-Refactor.