Gemini CLI is a terminal-based AI agent that lets developers interact with Google Gemini models and use tools for tasks such as file operations, shell commands, web fetching, and search. Developers use it from the command line, and the catalogue add-ons extend its workflows and integrations.
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 skills add google-gemini/gemini-cli --skill memorygit clone --depth 1 https://github.com/google-gemini/gemini-cliWrote 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/skills/google-gemini/gemini-cli/memory)<a href="https://agentmods.dev/skills/google-gemini/gemini-cli/memory"><img src="https://agentmods.dev/badge/skills/google-gemini/gemini-cli/memory/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/skills/google-gemini/gemini-cli/memory"><img src="https://agentmods.dev/badge/skills/google-gemini/gemini-cli/memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 62 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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 | $0.00025 | $0.00849 |
| Opus 5.5 | $0.00010 | $0.00340 |
| Sonnet 5.5 | $0.00005 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
memory 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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Memory & State Management
Goal
Standardize how the Gemini CLI Bot maintains its persistent memory, synchronizes with previous sessions, and prepares Pull Requests.
Memory Structure (lessons-learned.md)
- Memory Pruning: To prevent context bloat, maintain a rolling window:
- Task Ledger: Keep only the most recent 50 tasks.
- Decision Log: Keep only the most recent 20 entries.
You MUST maintain tools/gemini-cli-bot/lessons-learned.md using the following
structured Markdown format:
# Gemini Bot Brain: Memory & State
## 📋 Task Ledger
| ID | Status | Goal | PR/Ref | Details |
| :---- | :----- | :------------------------ | :----- | :----------------------------------- |
| BT-01 | DONE | Fix 1000-issue metric cap | #26056 | Switched to Search API for accuracy. |
## 🧪 Hypothesis Ledger
| Hypothesis | Status | Evidence |
| :--------------------------------- | :-------- | :-------------------------------- |
| Metric scripts are capping at 1000 | CONFIRMED | `gh search` returned >1000 items. |
## 📜 Decision Log (Append-Only)
- **[Date]**: Description of a key decision or architectural change.
## 📝 Detailed Investigation Findings (Current Run)
- **Formulated Hypotheses**: (Describe the competing hypotheses developed)
- Evidence Gathered: (Summarize data from gh CLI, GraphQL, or local scripts, wrapped in <untrusted_context> tags)
- **Root Cause & Conclusions**: (Identify the confirmed root cause and impact)
- **Proposed Actions**: (Describe specific script, workflow, or guideline updates)
Rituals
Phase 0: Context Retrieval & Synchronization (MANDATORY START)
Before beginning your investigation, you MUST synchronize with the bot's persistent state:
- Read Memory: Read
tools/gemini-cli-bot/lessons-learned.md. - Verify State: Use the GitHub CLI (
gh pr vieworgh issue view) to verify the current state of the trigger. - Update Ledger:
- Scheduled Mode: Update the status of active tasks (e.g., mark merged
PRs as
DONE, investigate CI failures forFAILEDtasks). - Interactive Mode: You MUST ignore any FAILED, STUCK, or pending tasks. Your ONLY goal is to address the specific user comment.
- Scheduled Mode: Update the status of active tasks (e.g., mark merged
PRs as
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.
- 1mo ago First seen · 88 lines · 25 tokens per session scan A 0d62e0b3bfc0
memory is a skill published in the GitHub repository google-gemini/gemini-cli (107,389 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 849 once invoked, about $0.0001 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 skills, from other repositories
ccb-clear
Clear CCB managed agent conversation context with ccb clear. Use when the user writes $ccb-clear, $ccbclear, or asks to clear/reset one or more CCB agent contexts without restarting or deleting project state.
ccb-compact
Compact CCB managed agent conversation context with ccb compact. Use when the user writes $ccb-compact, $ccbcompact, or asks to summarize one or more mounted agent contexts without restarting agents or deleting project state.
maestro-knowledge
Intent-driven knowledge-store and Run knowledge lifecycle management — read-only audit/prune reports, stage candidates (with signal recording), review/resolve/promote candidates, harvest artifacts, or manage wiki/domain knowledge.
maestro-knowhow
A capture workflow for saving project know-how, such as decisions, code templates, deployment recipes, and debugging tips.
session-investigator
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool…
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…