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.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersWrote 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/commands/wangke19/gemini-ai-helpers/save-session)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/save-session"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/save-session/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/commands/wangke19/gemini-ai-helpers/save-session"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/save-session.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 | $0.00010 | $0.01130 |
| Opus 5 | $0.00005 | $0.00565 |
| Sonnet 5 | $0.00002 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
save-session 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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
session:save-session
Synopsis
/save-session
/save-session [description]
Description
Saves the current conversation session to a comprehensive markdown file that enables seamless resumption of work after extended time intervals (days, weeks, or months).
This command addresses limitations of Gemini CLI's built-in session management by capturing:
- Complete conversation context and technical rationale
- Detailed file modification tracking with line numbers
- Key technical decisions and alternatives considered
- Commands executed during the session
- Clear resumption instructions
The generated session file is designed for engineers working across multiple projects with long gaps between sessions, providing all necessary context to continue work without losing momentum.
Implementation
The command follows a five-phase process:
Phase 0: Input Sanitization
If a description argument is provided, sanitize it for safe filename usage:
- Convert all spaces to hyphens
- Convert to lowercase
- Remove or replace special characters (keep only alphanumeric, hyphens, and underscores)
- Truncate to 100 characters maximum if longer
- Example: "investigating OCPBUGS-12345 regarding routes" → "investigating-ocpbugs-12345-regarding-routes"
Phase 1: Context Analysis
- Summarizes main topics and goals discussed
- Lists all accomplishments and completed tasks
- Identifies all files that were read, modified, or created
- Extracts important technical decisions and their rationale
- Captures any error messages encountered and how they were resolved
- Notes any commands that were run (make, linter, tests, etc.)
Phase 2: File Modification Tracking
- Reads and verifies current state of modified files
- Lists specific line numbers and code changes
- Includes before/after comparisons for critical changes
- Notes which files were created vs modified vs deleted
- Tracks any generated files (like bindata)
Phase 3: Session File Creation
Creates a comprehensive markdown document with these sections:
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.
- 9d ago First seen · 139 lines · 10 tokens per session scan A b3a9929023fc
save-session is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,130 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
notify
Poll the inbox for new notifications addressed to you.
wtfp:pause-writing
Record an exact context handoff so another session can resume without reconstructing intent.
gofer:side
Open a side conversation in the active CLI without disturbing the main pipeline state; resumable.
handover_chat
Salva o progresso da sessão atual em 07 - HANDOVERS/ ou em uma tarefa T0XX ativa.
cancel-ralph
Cancel active Ralph Loop.
checklist
Generate a custom checklist for the current feature based on user requirements.