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 adbertram/cli-tools --skill grokbot-sessions-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/grokbot-sessions-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/grokbot-sessions-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/grokbot-sessions-cli/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/adbertram/cli-tools/grokbot-sessions-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/grokbot-sessions-cli.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 | $0.00100 | $0.01960 |
| Opus 5.5 | $0.00040 | $0.00784 |
| Sonnet 5.5 | $0.00020 | $0.00392 |
| Haiku 4.5 | $0.00010 | $0.00196 |
Grade A, and why
grokbot-sessions-cli 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 today.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start>
The grokbot-sessions CLI follows this pattern:
grokbot-sessions <command-group> <action> [arguments] [options]
| Task | Command |
|---|---|
| Get one approval request | grokbot-sessions approvals get <APPROVAL_ID> |
| List permission requests and automatic review approvals | grokbot-sessions approvals list |
| Configure authentication credentials | grokbot-sessions auth login |
| Clear stored credentials | grokbot-sessions auth logout |
| Create a new profile from .env.example template | grokbot-sessions auth profiles create <NAME> |
| Delete a profile and its data | grokbot-sessions auth profiles delete <NAME> |
| Get details for a specific profile | grokbot-sessions auth profiles get <NAME> |
| List all profiles and show their auth types and active state | grokbot-sessions auth profiles list |
| Delete a profile and its data | grokbot-sessions auth profiles remove <NAME> |
| Rename a profile, re-keying its secrets to the new profile name | grokbot-sessions auth profiles rename <OLD> <NEW> |
| Activate a profile within its auth type | grokbot-sessions auth profiles select <NAME> |
| Check authentication status across profiles | grokbot-sessions auth status |
| Test authentication by verifying credentials work across profiles | grokbot-sessions auth test |
| Get one automation with its full record | grokbot-sessions automations get <AUTOMATION_ID> |
| List the automations attached to Grok Bot agents | grokbot-sessions automations list |
| Remove all cached responses | grokbot-sessions cache clear |
| Get one conversation with its decoded transcript entries | grokbot-sessions conversations get <CONVERSATION_ID> |
| List one conversation per agent generation, with entry and turn counts | grokbot-sessions conversations list |
| Get one implicit project | grokbot-sessions projects get <PROJECT_ID> |
| List Grokbot's implicit projects | grokbot-sessions projects list |
| Search every selected agent's transcript for a keyword | grokbot-sessions search run <QUERY> |
| Get one Grok Bot agent | grokbot-sessions sessions get <SESSION_ID> |
| List Grok Bot agents, one per session | grokbot-sessions sessions list |
| Search Grok Bot agents by name, title, description, or id | grokbot-sessions sessions search <QUERY> |
| Get one skill (never found: the API exposes no agent store) | grokbot-sessions skills get <SKILL_ID> |
| List agent-store skills (always empty: the API exposes no store) | grokbot-sessions skills list |
| Get one subagent surface, with the member's conversation summary | grokbot-sessions subagent-activity get <SUBAGENT_ID> |
| List room memberships and cursor-agent runs | grokbot-sessions subagent-activity list |
| Interleave every agent's transcript entries by timestamp, newest first | grokbot-sessions timeline consolidated |
| Get one decoded transcript entry | grokbot-sessions timeline get <ENTRY_ID> |
| List transcript entries, newest first within each agent | grokbot-sessions timeline list |
| Get one todo item (never found: Grokbot records none) | grokbot-sessions todos get <TODO_ID> |
| List todo items (always empty: Grokbot records none) | grokbot-sessions todos list |
| Get one derived tool call | grokbot-sessions tool-calls get <TOOL_CALL_ID> |
| List interactive card entries that stand in for Grokbot tool calls | grokbot-sessions tool-calls list |
| Get one turn with its entries in chronological order | grokbot-sessions turns get <TURN_ID> |
| List turns grouped from each agent's transcript, newest turn first | grokbot-sessions turns list |
| </quick_start> |
<essential_principles>
MANDATORY: Verify the live command shape before executing ANY grokbot-sessions command.
Consult the adjacent usage.json at
<cli-tools-root>/_repo/skills/grokbot-sessions-cli/usage.json, the live
grokbot-sessions --help / subcommand --help output, and README.md. Never
guess at command syntax.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today First seen · 128 lines · 100 tokens per session scan A 96efb671bc05
grokbot-sessions-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 1,960 once invoked, about $0.0004 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 2026-11-07.
grokbot-sessions-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grokbot-sessions-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 100 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| surfnicobailon/surf-cli | Skill | 684 | yesterday | MIT | A | 53 | Claude Code, Codex |
| rdc-cliBANANASJIM/rdc-cli | Skill | 193 | 14d ago | MIT | A | 82 | Claude Code, Codex |
| pixiv-cli-ciFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 61 | Codex |
| acrawl-mcpMingye-Lu/AgenticCrawler | Skill | 15 | yesterday | MIT | A | 200 | Claude Code, Codex |
| debug-hubrexleimo/aios | Skill | 62 | yesterday | MIT | B | 66 | Claude Code, Codex |