Create AI images, videos, music, and voice-over from one Agent Skill for Claude Code, Codex, and OpenClaw. The work is produced on the hosted, paid Beatra service
(mcp.beatra.ai).
This catalog entry is a reviewed pointer, not the executable package. It
contains no client code and performs no Beatra operation by itself. The package
it points to bundles three standard-library Python scripts that make network
calls and store a credential. It has no self-updater: it never downloads
code and never changes its own files. Read
Install and
Security & Safety Notes before activating it.
| Pinned identity | Value |
|---|---|
| Package | beatra 2.9.7 |
| Source commit | beatra-ai/ai-media-generator-skill@26a5f79 (full SHA 26a5f7963aca434c2cbced911a2914e3224c2107) |
| Package tree | f35935ef2d28c325c60471f6f0934ae1800fd1b0 (Git tree ID of skills/beatra at that commit) |
| License | MIT No Attribution (MIT-0) |
The pinned tree holds regular files only (no symlinks, no executable bits, no
binaries). Confirm that with the inspect commands below.
Explain that this fetches an external package from github.com, then ask
for approval. Only after approval:
set -e
umask 077
review_dir="$(mktemp -d)"
cd "$review_dir" || exit 1
git clone --quiet --filter=blob:none --no-checkout https://github.com/beatra-ai/ai-media-generator-skill.git src
git -C src checkout --quiet 26a5f7963aca434c2cbced911a2914e3224c2107 -- skills/beatra
test "$(git -C src rev-parse '26a5f7963aca434c2cbced911a2914e3224c2107:skills/beatra')" = 'f35935ef2d28c325c60471f6f0934ae1800fd1b0' && echo TREE-OK
Stop if the last command does not print TREE-OK. The expected commit and
tree IDs come from this catalog entry, not from the package or its website,
and Git addresses every fetched object by its hash.
git -C src ls-tree -r 26a5f7963aca434c2cbced911a2914e3224c2107 -- skills/beatra | awk '$1 != "100644"' # expect no output
grep -n -E 'maybe_auto_update|download_update|_apply_update' src/skills/beatra/scripts/mcp_client.py # expect no output
The first check lists any symlink, executable, or submodule entry; the second
finds the entry points of the self-updater that earlier versions shipped.
Report to the user what the review found: SKILL.md, manifest.json,agents/openai.yaml, install-source.json (the one-line marker {"schema_version":1,"source":"github"}),
the bundled Markdown references, and scripts/authorize.py,scripts/mcp_client.py, scripts/uninstall.py (Python 3.10+, standard
library only, no dependency installation, no lifecycle hooks). Summarize the
network, credential, local-state, telemetry, and version-notice behavior
listed under Security & Safety Notes.
The manifest and pattern scans above are only inventory aids. Before activation, read every file in the pinned tree, including each script, reference and hook, and inspect all dependency and network behavior. Do not claim source review from grep output. If complete review cannot be performed, stop before copying or executing; ask for a separate review rather than treating a digest as evidence of safety.
Ask for a second, separate approval, because this changes agent
configuration. Then copy the reviewed tree to the host's skills directory
(Claude Code shown; use the equivalent path for other hosts):
dest="$HOME/.claude/skills/beatra"
test ! -e "$dest" && test ! -L "$dest" || { echo "destination exists; stop and ask the user"; exit 1; }
cp -R "src/skills/beatra" "$dest"
There is no update switch to turn off in this version.
Authorization opens a browser sign-in and stores a bearer token. Ask first.
python3 "$dest/scripts/authorize.py"
Start a new agent session if the host discovers skills only at startup.
SKILL.md and its references; they define theroutes, payload shapes, and review loop.
beatra.models.list, task list) toread current model cards and credit estimates.
and which files will be uploaded. Wait for explicit approval. Planning or
"just do it" is not approval.
once with a stable client_request_id and poll the returned task.
billing.net_charged_credits, review theresult with the user, and ask again before any further paid stage.
python3 "$HOME/.claude/skills/beatra/scripts/mcp_client.py" verify
After the user approved the cost card for this exact payload, submit once with
a stable request id using the tool name from the installed SKILL.md. If the
response is lost, retry only with the same client_request_id and identical
arguments; never submit a replacement while the task is running.
This pinned version cannot update itself: it has no code that downloads or
replaces package files. update only reports what the store or tool that
installed the copy offers; for a copy installed by the steps above it finds
no such record and says to update the way you installed it. See the version
notice under Security & Safety Notes.
To move to a newer version, repeat Steps 1 to 3 for that commit in a new
review directory, show the user the file-level changes against the installed
copy (for example git -C src diff --stat 26a5f79 <new-commit> -- skills/beatra),
and replace the directory only after approval. A version not listed in this
entry has not been reviewed here.
dest="$HOME/.claude/skills/beatra"
python3 "$dest/scripts/uninstall.py" --dry-run
python3 "$dest/scripts/uninstall.py"
Read the JSON decision. disconnected means this was the last Beatra skill on
the device: the token was revoked (when revoked is true) and the filescredentials.json, installation.json, host.json, skills.json,network.json, balance-holds.json, pending_authorization.json, and.authorize.lock under ~/.beatra were removed. keep_connection means
another Beatra skill still uses the shared token, which stays.revoke_retry means the server refused the revocation and nothing changed;
run it again shortly. The script never deletes the package directory: after
confirming the path it prints with the user, delete $dest.
uninstall.py does not remove ~/.beatra/updates/. When the decision isdisconnected and no other Beatra skill is installed, remove that directory
and then the empty ~/.beatra; otherwise leave them. A token that could not
be revoked expires after 15 days idle and can be revoked at once in the
Beatra Console under Agents.
~/.beatra/credentials.json.upstream model providers and can change; the service is provided as is.
human review before publication.
a different review.
risk: critical is deliberate.
uses api.beatra.ai and tool calls go to mcp.beatra.ai; an upload is aPUT of the approved file to the HTTPS address the server returns, without
the bearer token. Unless a cached decision is still valid (10 minutes to 7
days), each run first asks https://api.beatra.ai/skill-route, and alsohttps://api.beatra.cn/skill-route when the first is slow or answers cn,
which network to use. These probes carry no credential or package identity.
When the answer is cn, authorization and tool calls go to api.beatra.cn
and mcp.beatra.cn with the same bearer token, and the version notice
reads from www.beatra.cn; Beatra serves these .cn hosts from mainland
China.python3 "$dest/scripts/mcp_client.py" network --use ai pins the .ai
hosts and stops the probes; a failed version-notice read can still retry
once on the other network.
or replaces package files and writes nothing inside the install directory.
Before verify, tools, upload, or call, at most once every 24 hours
per install path, it records the check time and looks, read-only, for
records another installer left beside the package (ClawHub origin.json,
SkillHub or skills CLI lock entries, gh skill frontmatter). A copy
installed by the steps above normally has none and makes no request. When
one is found, it reads https://beatra.ai/skills/beatra/sources.json
(no credential, 3-second timeout, 64 KiB cap) and, if that installer offers a
newer version, prints one line to stderr with the installer's own update
command. It never runs the command.
and forwarded to the third-party model provider executing the task. Beatra
runs the service outside mainland China; on the cn route (see Network)
requests reach it through Beatra's hosts in mainland China. See the
privacy policy.
for reasons attributable to Beatra or the upstream model are returned
automatically; otherwise purchases are non-refundable, and actual usage can
exceed the estimate and leave a negative balance. See the
terms.
authorize.py runs an OAuth device flow, opens the browseron the approval page, and stores one bearer token in~/.beatra/credentials.json (directory 0700, file 0600). The token never
goes into argv, environment variables, or output. It carries full Beatra
scope, including wallet:spend, has a sliding 15-day idle lifetime, and is
shared by every Beatra skill on the device. While the user has not yet
selected Allow, the pending device code is kept in~/.beatra/pending_authorization.json (0600) so a rerun finishes the same
approval instead of opening a new one. When verify, tools, upload, orcall finds no working token, the client makes one check of that saved
approval and stores the token if the user has already selected Allow; it
never starts a new authorization or opens a browser.
~/.beatra/ also holds installation.json (randominstallation reference), host.json (agent platform and hostname),skills.json (installed Beatra skill paths), network.json (route
decision, with a country code when the route answer includes one),balance-holds.json (after an insufficient-credit refusal, that tool is
answered locally for up to 30 minutes; call --recheck-balance sends one
call), a short-lived .authorize.lock, and, per install path,updates/<id>/state.json (last version check), source.json (install
source), and registration.json (last registration). Files are 0600
except host.json, which follows the umask.
package slug and version, the detected agent platform (for exampleclaude-code, from environment variables), and the installation reference.
After connecting, at most once a day unless the version, platform, route, or
install source changes, the client makes a non-billablebeatra.installations.register call with those package and platform
fields, the release channel, the network route, the install source
(github for this tree), and coarse runtime facts: OS and OS version, CPU
architecture, Python version, locale, and UTC offset. Every tool call addssource_package_slug and source_platform. There is no opt-out for these
fields.
records, artifacts, and billing ledgers are retained after account closure
for audit and tax purposes.
rights in outputs; they must hold rights to uploaded media and must not
create deceptive impersonations.