metergraph-skills
Installs the Metergraph agent skill into a project, so Codex, Claude Code or
Cursor can load it. This is the Python equivalent of metergraph skill in the
npm CLI (metergraph-cli).
This package does not sign in, connect a workspace, configure MCP or make any
network request. For those, use the npm CLI: npx metergraph-cli@next. The
Python SDK for instrumenting an application is a different package,
metergraph.
Install the skill
pip install metergraph-skills
metergraph-skills install --client claude --runtime local
Run it in the project directory, or pass --project DIR.
| Option | Values |
|---|---|
--client |
codex, claude, cursor |
--runtime |
local, cloud |
--project |
Project directory. Default: the current directory. |
--json |
Print one JSON line on stdout. |
The skill is written to the client's project skill directory:
| Client | Path |
|---|---|
| Codex | .agents/skills/metergraph/SKILL.md |
| Claude Code | .claude/skills/metergraph/SKILL.md |
| Cursor | .cursor/skills/metergraph/SKILL.md |
An ownership receipt is written to .metergraph/skill-installations.json. It
holds no secrets. No other file is touched. Restart the client afterwards; the
skill is not discovered until the client loads it.
Use metergraph-skills update to replace an older revision installed by
Metergraph. A skill file that Metergraph did not install, or that was edited
after it was installed, is never replaced.
Same files as the npm CLI
metergraph-skills and metergraph skill write the same paths and the same
receipt. A skill installed by one is recognised and updated by the other. The
bundled SKILL.md is byte-identical to the one in the npm package and to
https://www.metergraph.dev/SKILL.md for the same revision, and its SHA-256
is checked before anything is written.
To copy the file yourself, metergraph-skills path prints the directory that
holds the bundled SKILL.md and manifest.json.
Exit codes
| Code | Outcome |
|---|---|
| 0 | ok |
| 1 | internal_error: the bundled skill failed its integrity check |
| 2 | invalid_input |
| 6 | unsupported: the client or runtime cannot load project skill files |
| 8 | conflict: an existing file was not replaced |
| 9 | filesystem_error |
License
Apache-2.0. Source: https://github.com/metergraph/cli.
Metadata
Release files for metergraph-skills 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| metergraph_skills-0.1.0.tar.gz | 23.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| metergraph_skills-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 44.9 kB
Release files / metergraph_skills-0.1.0.tar.gz
| Download URL | metergraph_skills-0.1.0.tar.gz |
|---|---|
| Size | 23.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4ee84f6272ff70041822bf64c8da1b1b2ddc897a7bdc2343924d6b4a19ec4cf4
|
|
BLAKE2b-256 checksum How to use checksums |
2cda6dfe1574fe4fedd2f7b7e6c5b2aa7af47b58f91784be5e33d396a892b81a
|
| 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 8, 2026.
Transparency logRelease files / metergraph_skills-0.1.0-py3-none-any.whl
| Download URL | metergraph_skills-0.1.0-py3-none-any.whl |
|---|---|
| Size | 21.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a0a93393d99c19235d3bfef8c23fed2e8ec382cd4a70a294134a25497d0c02ac
|
|
BLAKE2b-256 checksum How to use checksums |
0274e2928a1dd527421b424ccca7dc5e5287b4f7b5d1a0a7352ddc66b02dbc2d
|
| 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 8, 2026.
Transparency log