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 instructions/eai-support/eai-gofer/copilot-instructionsgit 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/instructions/eai-support/eai-gofer/copilot-instructions)<a href="https://agentmods.dev/instructions/eai-support/eai-gofer/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/eai-support/eai-gofer/copilot-instructions.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 | $0.00557 | $0.00557 |
| Opus 5 | $0.00279 | $0.00279 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
eai-gofer copilot-instructions.md 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
Project Overview
gofer is a Unknown project.
Gofer Pipeline
This project uses Gofer for spec-driven development. In GitHub Copilot Chat, use
#eai to start or continue the core pipeline: Gofer Start -> research ->
specify -> plan -> tasks -> implement -> validate.
Gofer routes internally through .specify/commands/*.md contracts, so numbered
stage prompts stay hidden unless explicitly needed for internals. Before EAI
readiness, classify the request: app delivery continues directly, while clear
non-app work asks once before skipping EAI tenant/app setup. Validation is the
terminal quality gate and includes the final engineering review loop. Artifacts
live in .specify/specs/{feature}/.
Token And Cost Policy
- Treat
.specify/memory/gofer-model-policy.yamlas the repo-owned model policy. Use CopilotAutofor simple/default work unless the user explicitly chooses a specific model. - Use the cheapest capable model first. Prefer compact Copilot prompts and built-in workspace context; only choose paid/high-tier chat models when the task is ambiguous, security-sensitive, release-critical, or a cheaper pass fails.
- Keep raw command and search output out of chat context. Save durable summaries
to
.specify/specs/{feature}/context-bundle.mdand continue from artifacts. - Reuse stable non-secret prefixes for provider caching where supported: Gofer scaffold, AGENTS/Copilot instructions, constitution, repo map, stage contracts, and validation rubric.
- After large research, planning, implementation, or validation bursts, checkpoint artifacts and compact/clear/resume context when the host supports it.
Code Quality
Code Conventions
- Follow existing code style and naming conventions in this project
- Write clear, self-documenting code with descriptive names
- Keep functions focused and small
- Add comments only where the logic is not self-evident
- Handle errors at appropriate boundaries
Task Management
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.
- 4d ago First seen · 63 lines · 557 tokens per session scan A ea6d48e0e971
eai-gofer copilot-instructions.md is an instructions file published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 557 tokens to every session, about $0.0028 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 instructions, from other repositories
agent-levers AGENTS.md
Instructions for fmind/agent-levers, covering agents.md, conventions, workflow and layout.
agent-evolutions AGENTS.md
AGENTS.md instructions for fmind/agent-evolutions, covering agents.md, conventions, workflow and layout.
agent-levers CLAUDE.md
Instructions for fmind/agent-levers, a project described as: Levers for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — multiply the agent's force, divide the human's effort.
agent-levers GEMINI.md
Instructions for fmind/agent-levers, a project described as: Levers for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — multiply the agent's force, divide the human's effort.
agent-evolutions CLAUDE.md
Claude Code instructions for fmind/agent-evolutions, a project described as: Genetic exploration of solution spaces for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — gather a verifiable objective, evolve variants, apply the winner.
agent-evolutions GEMINI.md
Gemini CLI instructions for fmind/agent-evolutions, a project described as: Genetic exploration of solution spaces for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — gather a verifiable objective, evolve variants, apply the winner.