Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add arenadata/adcm-agent/plugin install adcmWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/arenadata/adcm-agent/adcm-review)<a href="https://agentmods.dev/commands/arenadata/adcm-agent/adcm-review"><img src="https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-review.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00018 | $0.00440 |
| Opus 5 | $0.00009 | $0.00220 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
adcm-review 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 6d 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.
What it actually says
Review the bundle change. Scope: $ARGUMENTS
Delegate to the adcm-bundle-reviewer agent — it carries the full checklist. Use this command directly only for a change small enough to read in one pass.
Establish the diff
git diff, the named range, or the files given. Review what is there. Read the
repository's spec.yaml first: the editions, the excludes and the splitter list decide
which half of the checklist applies.
Verify mechanically, do not only read
ADCM_SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
.adcm/venv/bin/python "$ADCM_SCRIPTS/bundle_build.py" --check
.adcm/venv/bin/python "$ADCM_SCRIPTS/bundle_check.py"
When the diff touches a splitter source, read the rendered result in
.adcm/staging/<edition>/. A YAML merge key or a Jinja conditional often does not produce
what the source appears to say, and what ships is what matters.
The findings that matter here
Generated file edited without its auto_bump source. An edition exclude that drops or
leaks a file. Build-time Jinja mixed with runtime Ansible Jinja. An action combining
states: and masking:, or whose on_fail: strands the object. An hc_acl action whose
playbook ignores the .add group. A config change that gives every already-deployed
cluster a blocking concern at upgrade. A credential typed as string. A host name, URL or
password hardcoded anywhere.
Do not upload or deploy as part of a review unless asked.
Report
Findings only, most severe first: file and line, the mechanism, and a concrete scenario. Separate confirmed defects from what needs a live instance to check. If there is nothing, say so and list what you checked.
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.
- 6d ago First seen · 45 lines · 18 tokens per session scan A 465ff81cf8c2
adcm-review is a command published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 18 tokens to every session and 440 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.