Skip to main content

familiar

pypi docs

compose and invoke ai agent prompts from reusable conjurings and invocations.

ships with a standard set of conjurings and invocations, or bring your own (mine are very much wip).

installation

pip install familiar-cli

usage

usage: familiar [-h] [--version] [--debug] {conjure,invoke,list,lint} ...

conjure and invoke familiars

positional arguments:
  {conjure,invoke,list,lint}
    conjure             compose system instructions for an agent
    invoke              render an invocation and run the agent
    list                list available conjurings and invocations
    lint                lint conjurings and invocations

options:
  -h, --help            show this help message and exit
  --version             show program's version number and exit
  --debug               show full traceback on error

conjure conjurings to create system instructions for an agent:

familiar conjure codex rust infra sec

save composed conjurings as a reusable claude subagent:

familiar conjure claude python sec --save-subagent
familiar conjure claude rust infra --save-subagent --subagent-name ship_ops

save an invocation as a reusable skill:

familiar invoke claude code-review --save-skill
familiar invoke codex refactor src/foo.py --save-skill --skill-name cleanup_refactor

invoke an action prompt:

familiar invoke codex bootstrap-rust myapp lib 1.78 mit

run in a separate git worktree to avoid interfering with local changes:

familiar invoke --worktree codex bootstrap-rust myapp lib

list available conjurings and invocations:

familiar list

lint conjurings and invocations, including local .familiar/ overrides:

familiar lint

customization

add your own conjurings and invocations by creating files in .familiar/ in your repo:

.familiar/
  conjurings/
    myprofile.md      # new conjuring
    rust.md           # override built-in
  invocations/
    my-task.md        # new invocation

local files take precedence over built-ins.

plugins

add new agents via plugins:

pip install familiar-gemini
familiar invoke gemini bootstrap-python myapp cli

see the plugin docs for creating your own.

placeholders

invocations support placeholders:

  • $1, $2, ... - positional arguments
  • $ARGUMENTS - all positional arguments joined
  • {{key}} - named arguments passed via --kv key=value

documentation

full docs at familiar.readthedocs.io.

license

mit

Metadata

Release files for familiar-cli 0.6.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for familiar-cli 0.6.2
File Size Uploaded Provenance
familiar_cli-0.6.2.tar.gz 58.7 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for familiar-cli 0.6.2
File Interpreter ABI Platform
familiar_cli-0.6.2-py3-none-any.whl Python 3 none any Details

Total release size: 107.0 kB

Release files / familiar_cli-0.6.2.tar.gz

Download URL familiar_cli-0.6.2.tar.gz
Size 58.7 kB
Tags Source
SHA-256 checksum
How to use checksums
268f8d37ec0e0c10b8ed9baa3f1cb93e740982181e08a609b5ba9c256657c3d5
BLAKE2b-256 checksum
How to use checksums
39d5592fea5f7b900832a47fac1e985cb7a9ac8e46849fdc71077a37621d968d
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 13, 2026.

Transparency log

Release files / familiar_cli-0.6.2-py3-none-any.whl

Download URL familiar_cli-0.6.2-py3-none-any.whl
Size 48.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
37fc31154a60db59d02585d8ade08c46be91684eaa46d46681998f5df2564a92
BLAKE2b-256 checksum
How to use checksums
869037250754fb6dcb9cadf7f483f741a274ca49600c72d1ec25ddd452c06f71
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 13, 2026.

Transparency log

Security for familiar-cli 0.6.2

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.

Select from 2 files

Attestation for familiar_cli-0.6.2.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 13, 2026.

Transparency log

A 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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page