Borrowing it
Nothing to install: this file belongs to IgorGanapolsky/ThumbGate. 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/IgorGanapolsky/ThumbGate/main/GEMINI.mdgit clone --depth 1 https://github.com/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/gemini-md)<a href="https://agentmods.dev/instructions/igorganapolsky/thumbgate/gemini-md"><img src="https://agentmods.dev/badge/instructions/igorganapolsky/thumbgate/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/igorganapolsky/thumbgate/gemini-md"><img src="https://agentmods.dev/badge/instructions/igorganapolsky/thumbgate/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 | $0.01438 | $0.01438 |
| Opus 5.5 | $0.00575 | $0.00575 |
| Sonnet 5.5 | $0.00288 | $0.00288 |
| Haiku 4.5 | $0.00144 | $0.00144 |
Grade A, and why
ThumbGate 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 22d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - ThumbGate Source
See CLAUDE.md and AGENTS.md.
When using Gemini inside this repo, use the local dev ThumbGate wiring defined in .mcp.json.
Key: Always dogfood the latest local changes before publishing.
Session PR Management and System Hygiene
- Start with
bin/agent-loop --health --json(fail closed), then read all three repo directives, query local ThumbGate memory, and inspect open PRs, open GitHub Issues, remote branches, worktrees, and currentmainCI. - Reconcile GitHub Issues and Actions plus available Linear AI, Obsidian vault,
and standalone GitHub Copilot CLI surfaces. Close or advance actionable
Issues in the same session — do not leave the Issues board untouched while
only draining PRs. Record unavailable local integrations and continue with
deterministic
gh, git, and repository checks, which remain authoritative. - Merge only review-complete PRs with terminal-green required checks, using
npm run pr:manageand Trunk. Never approve, dismiss, bypass, or weaken a human-review or branch-protection requirement. - Classify orphan branches before cleanup and preserve unique commits before deleting a branch or worktree.
- Verify required CI on the exact resulting
mainSHA and run the standard clean-worktree suite before any completion claim. - Record session lessons in local ThumbGate memory and report whether the memory and ML feedback pipeline helped or hindered the work.
- Use the mandatory completion sentence from
AGENTS.mdonly when every PR, cleanup, CI, dry-run, and lesson-recording item is verified; otherwise report blockers without claiming session completion.
NEVER Bypass Branch Protection (ABSOLUTE)
NEVER approve a pull request. NEVER satisfy, dismiss, or disable a branch-protection requirement on the owner's behalf. NEVER use --admin, --force, or an owner credential to make a merge possible that would otherwise be blocked.
Everything merges through PRs under the configured branch protection. When human review is required, only a human may satisfy it. Report the blocker with evidence. Non-mutating diagnosis and a separate policy-change PR are allowed, but stop before any action that mutates review or protection state. Never route around the control.
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.
- 22d ago Changed · +9 lines · +162 tokens per session 7db23e820b2a
- 1mo ago Changed · +6 lines · +89 tokens per session 9d3acbe934a9
- 1mo ago First seen · 81 lines · 1,187 tokens per session scan A 8febf23b9765
ThumbGate GEMINI.md is an instructions file published in the GitHub repository IgorGanapolsky/ThumbGate (29 stars, last pushed yesterday), licensed MIT. It adds 1,438 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
plan-forge landing-zone.instructions.md
Azure Landing Zone baselines — identity, network, policy, management, security, tagging, subscription organization.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).