Borrowing it
Nothing to install: this file belongs to thoreinstein/gemini-beads. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thoreinstein/gemini-beads/main/GEMINI.mdgit clone --depth 1 https://github.com/thoreinstein/gemini-beadsWrote 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/thoreinstein/gemini-beads/gemini-md)<a href="https://agentmods.dev/instructions/thoreinstein/gemini-beads/gemini-md"><img src="https://agentmods.dev/badge/instructions/thoreinstein/gemini-beads/gemini-md/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/instructions/thoreinstein/gemini-beads/gemini-md"><img src="https://agentmods.dev/badge/instructions/thoreinstein/gemini-beads/gemini-md.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 | $0.00473 | $0.00473 |
| Opus 5.5 | $0.00189 | $0.00189 |
| Sonnet 5.5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
gemini-beads GEMINI.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 2mo 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.
What it actually says
Beads - Persistent Task Memory
You have access to Beads (bd), a graph-based issue tracker that provides persistent memory for multi-session work.
Core Mandates for Beads
- Use
run_shell_commandto executebdcommands. - Source of Truth: The
bdtool is the authority. - Persistence: Always ensure work is tracked in beads so it survives conversation compaction.
When to use Beads (bd)
YES - Use bd when:
- Work spans multiple sessions or days.
- Tasks have dependencies or blockers.
- You need to recover context after a long break.
- You are collaborating with a team.
NO - Do not use bd when:
- Tasks are strictly linear and single-session.
- You are just "exploring" without a concrete goal.
Session Protocol (The Workflow)
- Start: Run
bd readyto find unblocked work. - Context: Run
bd show <id>to get full details for a task. - Work: Run
bd update <id> --claimto claim and start work atomically. - Finish: Run
bd close <id> --reason "..."when done. - Save: Run
bd sync(orgit pushif using Dolt/JSONL backend) to persist changes.
Key Commands
bd prime: Outputs AI-optimized workflow context (Project, User, Recent Issues). Run this first if you lack context.bd create "Title" [type] [priority]: Create a new issue.bd ready: Find unblocked work.bd show <id>: Show details for a specific issue.bd update <id> --claim: Claim and start work.bd sync: Persist changes to git.
Agent Behavior
- Proactive Tracking: If the user asks you to work on something substantial, suggest creating a bead for it: "Shall I track this in beads?"
- Compaction Recovery: If the conversation history is lost/compacted, run
bd primeto re-orient yourself.
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.
- 2mo ago First seen · 44 lines · 473 tokens per session scan A 4b955d7bb6d2
gemini-beads GEMINI.md is an instructions file published in the GitHub repository thoreinstein/gemini-beads (25 stars, last pushed 8mo ago), licensed MIT. It adds 473 tokens to every session, about $0.0019 per session on Opus 5.5. 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.
gemini-beads GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gemini-beads GEMINI.mdthoreinstein/gemini-beads | Instructions file | 25 | 8mo ago | MIT | A | 473 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |