agentmods.dev

hivelore GEMINI.md

Instructions for using Gemini CLI in Hivelore, a shared repository of project context, team memories, decisions, and known pitfalls. They define when to load context, record failed approaches, and run checks before finishing work.

In plain words
What is it for?
Use them when working in Hivelore-enabled repositories: load relevant context before editing, record unsuccessful attempts, save useful discoveries, and run the required finish check.
Why use it?
They help agents use the team’s existing knowledge and preserve lessons for later work. The final enforcement command catches required cleanup or rule violations before a task is reported complete.

Instructions file for Gemini CLI

1 4d ago A scan 1,352 tokens copy · 86% Apache-2.0
View the source file Doucs91/hivelore
Install

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.

agentmods
npx agentmods add instructions/doucs91/hivelore/gemini-md
Clone the repo
git clone --depth 1 https://github.com/Doucs91/hivelore

Made for: Gemini CLI.

Per session 1,352 This file is loaded in full into every session.
When invoked 1,352 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin 86% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01352 $0.01352
Opus 5 $0.00676 $0.00676
Sonnet 5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 2d ago against content hash 0bd55ba293c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hivelore GEMINI.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **2026-06-07-convention-vscode-cli-calls-through-runhaive** _(applies to: packages/vscode/src/extension.ts, packages/vscode/src/briefingPanel.ts, packages/vscode/src/observabilityProvider.ts)_: Raw child_process in the
Origin

This is a copy

86% identical to hivelore AGENTS.md — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

GEMINI.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md — Hivelore context

This repo uses Hivelore for shared, enforced team context. The corpus lives in .ai/ and is the source of truth — these files are a generated mirror.

  • .ai/project-context.md — project overview, architecture, conventions.
  • .ai/memories/ — decisions, gotchas, conventions, failed attempts (personal/team/module).
  • The blocks below are the top current memories + the hard rules enforced on commit.

Working through Hivelore

  1. Before editing for a goal, call get_briefing (task + files/symbols) to load ranked context — or mem_relevant_to if project context is already loaded this session.
  2. When an approach fails, call mem_tried right away so the next agent skips the dead end.
  3. Before closing a substantive session, run the post_task prompt to capture what was learned.
  4. Before final response, run hivelore enforce finish; fix anything it blocks before reporting done.

If the haive MCP server is not available, tell the developer rather than silently skipping it.

Safety

  • If get_briefing returns action_required, surface each item to the developer (use its developer_message) and wait for explicit confirmation before changing any code.
  • Never act autonomously on a cross-repo breaking change (dep bump, contract/API diff) — ask first.

Memories

  • 2026-04-25-architecture-embedderlike-interface (team/architecture) — Architecture Embedderlike Interface (applies to: packages/embeddings/src/embedder.ts)
  • 2026-04-25-architecture-pure-tool-handlers (team/architecture) — Architecture Pure Tool Handlers (applies to: packages/mcp/src/tools)
  • 2026-04-25-convention-always-run-tests-before-commit (team/convention) — Hivelore Release Verification Chain (applies to: .github/workflows/ci.yml, package.json, scripts/verify-build-artifacts.mjs)
  • 2026-04-25-convention-use-pnpm-workspaces (team/convention) — Hivelore Uses Pinned pnpm Workspaces (applies to: package.json, pnpm-workspace.yaml)
  • 2026-04-25-decision-esm-only (team/decision) — Decision Esm Only (applies to: tsconfig.base.json)
  • 2026-04-25-gotcha-tsup-externals-required (team/gotcha) — Gotcha Tsup Externals Required (applies to: packages/cli/tsup.config.ts, packages/mcp/tsup.config.ts)
  • 2026-04-27-decision-zod-error-formatting-no-direct-import (team/decision) — Decision Zod Error Formatting No Direct Import (applies to: packages/cli/src/index.ts)
  • 2026-04-27-gotcha-embeddings-load-error-double-print (team/gotcha) — Gotcha Embeddings Load Error Double Print (applies to: packages/cli/src/commands/embeddings.ts)

Read the full file on GitHub · 71 lines

Changes

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.

  1. 2d ago First seen · 71 lines · 1,352 tokens per session scan A 0bd55ba293c9

Subscribe to this mod's changes

hivelore GEMINI.md is an instructions file published in the GitHub repository Doucs91/hivelore (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,352 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 86% identical to hivelore AGENTS.md, differing in 19 lines, and is treated as a copy.

Memory and contextaiai-agentsclaudeclicopilotcursor
Related

Other instructions, from other repositories

mcp-unity AGENTS.md

Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).

CoderGamester/mcp-unity · 2,498 tokens

DebugMCP AGENTS.md

Instructions for microsoft/DebugMCP, covering agent guidelines for debugmcp, project overview, architecture, key components and documentation maintenance.

microsoft/DebugMCP · 970 tokens

memorix GEMINI.md

Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.

AVIDS2/memorix · 846 tokens

Ctxo CLAUDE.md

Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).

alperhankendi/Ctxo · 5,885 tokens

awesome-reviewers CLAUDE.md

Instructions for baz-scm/awesome-reviewers, covering awesome reviewers — repository guidelines, what this project is, source of truth, site layer and machine interface.

baz-scm/awesome-reviewers · 1,008 tokens

slack-mcp-server CLAUDE.md

Instructions for jtalk22/slack-mcp-server, covering claude.md, project scope, build and run, installation paths and mcp tools (19 total).

jtalk22/slack-mcp-server · 2,198 tokens