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 commands/thrashr888/agentkernel/sessionsgit clone --depth 1 https://github.com/thrashr888/agentkernelWhat 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 | $0.00000 | $0.00665 |
| Opus 5 | $0.00000 | $0.00332 |
| Sonnet 5 | $0.00000 | $0.00133 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
sessions 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 2d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentkernel session
Manage agent sessions. A session ties together a sandbox, an agent type, and lifecycle metadata (creation time, exec count, status). Sessions can be stopped, saved (snapshotted), and resumed.
Subcommands
| Command | Description |
|---|---|
session start --name NAME --agent AGENT [-B BACKEND] |
Start a new session |
session list |
List all sessions |
session stop <NAME> |
Stop a session (stops sandbox, keeps metadata) |
session save <NAME> |
Save a session (snapshot sandbox + mark saved) |
session resume <NAME> |
Resume a stopped or saved session |
session delete <NAME> |
Delete a session and clean up |
Examples
Start a session
agentkernel session start --name feature-x --agent claude -B docker
# Output:
# Session 'feature-x' started.
# Sandbox: session-feature-x
# Use: agentkernel attach session-feature-x
The sandbox is named session-<name>. Use exec to interact with any supported
backend. Interactive attach is available only on backends that support it;
server-owned Firecracker sessions use agentkernel exec session-<name> -- <command> or agentkernel ssh session-<name> when SSH is configured.
List sessions
$ agentkernel session list
NAME AGENT STATUS DURATION EXECS
feature-x claude running 2h 14m 5
bugfix-123 gemini saved 1d 12
old-session codex stopped 3d 0
Work in a session
agentkernel exec session-feature-x -- python3 -c "print('working')"
# Docker and other interactive-attach backends only:
agentkernel attach session-feature-x
Save a session (snapshot)
# Creates a snapshot and marks the session as saved
agentkernel session save feature-x
# Output: Session 'feature-x' saved (snapshot: feature-x-20260201)
Resume a session
# Restarts the sandbox and marks session as running
agentkernel session resume feature-x
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.
- 2d ago First seen · 98 lines · 0 tokens per session scan A ff07197d6a5c
sessions is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 665 tokens. 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 commands, from other repositories
diagnose
Run sivtr doctor to check the environment, then investigate any failing checks.
test-changed
Run the full quality gate on only the files changed since branching from main.
test_mcp
Test all rust-docs-testing tools found in @rust-docs-mcp/src/service.rs.
update_mcp_tools_list
Read the rust-docs-mcp/src/service.rs module and ensure that the README.md and the rust-docs-mcp/install.sh files have up to date lists of the tools available in the MCP.
review
You are an expert code reviewer. Your job is to review code changes and provide actionable feedback.
speckit.git.feature
Create a feature branch with sequential or timestamp numbering.