Agent Shell
Agent Shell is a light weight abstraction for executing a cli coding agent headlessly and returning the output that can be used programatically as a unified contractFeatures
- One unified contract — the same
execute,stream,health_check, andlist_modelsAPI across every agent; swap the backend without changing consuming code. - Seven CLI agents — Claude Code, OpenCode, Copilot CLI, Codex, Pi, Cursor, and Grok behind a common adapter protocol.
- Execute or stream — get one
AgentResponse(raisesAgentExecutionErroron a failed run), or async-iterate normalizedStreamEvents with optional thinking/reasoning. - Composable execution policy — preserve native execution by default, or opt into Linux PID namespace isolation without changing an agent adapter.
- Session resumption — continue any conversation by passing back its
session_id. - Normalized cost & tokens — consistent
costandoutput_tokens(reasoning included) regardless of how each CLI reports them. - Model discovery — retrieve the exact account/workspace-aware model strings accepted by each CLI, without inference calls, SDK dependencies, or static catalogs.
- Health checks — confirm an agent + model combination actually works before you rely on it, read from the event stream rather than unreliable exit codes.
- Portable tool control — one canonical allow/deny vocabulary
(
bash, edit, read, web_search, web_fetch) translated to each CLI's own tool names. - Unified MCP management — register, remove, and list MCP servers across agents through a single API.
- Package management — install/register, list, and remove harness packages through a shared API, with Pi as the first supported agent.
- Async & dependency-free — pure
asyncio, zero runtime dependencies, Python 3.12+.
Installation
uv add agent-shell-py
or with pip:
pip install agent-shell-py
Agent skills
The repository includes reusable skills that teach coding agents how to use AgentShell:
invoking-cli-agents— invoke, stream, resume, and restrict CLI agents.delegating-code-review— delegate an independent code review through AgentShell.
Install them interactively with the Vercel Skills CLI:
npx skills add ScottRBK/agent-shell
Or install both skills globally for every coding agent supported by AgentShell:
npx skills add ScottRBK/agent-shell --global \
--skill '*' \
--agent claude-code opencode github-copilot codex pi cursor grok \
--yes
Install only the core AgentShell skill with:
npx skills add ScottRBK/agent-shell --skill invoking-cli-agents
The skills provide agent instructions. Install agent-shell-py and the chosen coding-agent CLIs
separately.
Examples
Execute
from agent_shell.shell import AgentShell
from agent_shell.models.agent import AgentType
shell = AgentShell(agent_type=AgentType.CLAUDE_CODE)
response = await shell.execute(
cwd="/path/to/project",
prompt="Can you tell me about this project?",
allowed_tools=["Read", "Glob", "Grep"],
model="sonnet",
)
print(response.response)
print(f"Cost: ${response.cost:.4f}")
print(f"Output tokens: {response.output_tokens}") # billed output, reasoning included
print(f"Session: {response.session_id}")
# Resume the conversation using the session_id
follow_up = await shell.execute(
cwd="/path/to/project",
prompt="Now refactor the auth module based on your findings",
allowed_tools=["Read", "Edit", "Bash"],
model="sonnet",
session_id=response.session_id,
)
output_tokensis a cost measure: the billed output-token count, which includes reasoning tokens (they are billed at the output rate). It is reported consistently across all adapters.
See more examples for isolation and execution hosts, failure handling, streaming, model discovery, health checks, tool restrictions, MCP servers, packages, and logging.
1 maintainer
Metadata
1 maintainer
Release files for agent-shell-py 0.5.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| agent_shell_py-0.5.0.tar.gz | 798.0 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent_shell_py-0.5.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 919.7 kB
Release files / agent_shell_py-0.5.0.tar.gz
| Download URL | agent_shell_py-0.5.0.tar.gz |
|---|---|
| Size | 798.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
987cdc093587c80c2304efd6735485c79538de190664a54caa25b29fa1bb717e
|
|
BLAKE2b-256 checksum How to use checksums |
73c406d2869a72171955281c97d80eb8a200bbc0789236d4dd3b45a4d53fdfe9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 15, 2026.
Transparency logRelease files / agent_shell_py-0.5.0-py3-none-any.whl
| Download URL | agent_shell_py-0.5.0-py3-none-any.whl |
|---|---|
| Size | 121.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
57b0b8b8aa87ab165f1bcf301c2da447e3bae97afd9a69ed074a75ffcff59f43
|
|
BLAKE2b-256 checksum How to use checksums |
21209fc8a6b53ea9f23e1fb704920188cfa8f495a7a6b2d5338a59e3f3869777
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 15, 2026.
Transparency logSecurity for agent-shell-py 0.5.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for agent_shell_py-0.5.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 15, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
