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/thoreinstein/gemini-beads/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.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 | $0.00473 | $0.00473 |
| Opus 5 | $0.00236 | $0.00236 |
| Sonnet 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 5d 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.
- 5d 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 (26 stars, last pushed 6mo ago), licensed MIT. It adds 473 tokens to every session, about $0.0024 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 2026-08-30.
Other instructions, from other repositories
gemini-time-injector GEMINI.md
Gemini CLI instructions for kongyo2/gemini-time-injector, covering time-injector extension and how to use this information.
gemini-faf-mcp AGENTS.md
Instructions for Wolfe-Jam/gemini-faf-mcp, covering agents.md — gemini-faf-mcp, project, instructions for ai agents, context and stack.
gemini-extension GEMINI.md
Instructions for OilpriceAPI/gemini-extension, covering oilpriceapi grounding instructions, ground product answers, route data requests, present data precisely and recover from failures.
gemini-mem GEMINI.md
Instructions for djinn-soul/gemini-mem, covering gemini.md, memory behavior and operator notes.
branched-openspec AGENTS.md
Instructions for tomkyle/branched-openspec, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
gemini-redteam GEMINI.md
Gemini CLI instructions for Baba01hacker666/gemini-redteam, covering red team gem — security research context, baseline behavior, domain coverage, output style and response quality standard.