Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/arenadata/adcm-agent/adcm-buildgit clone --depth 1 https://github.com/arenadata/adcm-agentWrote 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-build)<a href="https://agentmods.dev/commands/arenadata/adcm-agent/adcm-build"><img src="https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-build.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 | $0.00019 | $0.00576 |
| Opus 5 | $0.00010 | $0.00288 |
| Sonnet 5 | $0.00004 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
adcm-build 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the bundle in this repository. Mode: $ARGUMENTS
Load the adcm-bundle-build skill — it owns spec.yaml semantics, the flags and the
error table. Do not assemble a packer by hand.
Pick the mode
- check (default when you are iterating) — render and validate only, about a second.
This is the compile check for a bundle refactor; run it after every edit to a
.j2the splitter owns. - dev — a real archive with a unique version, for uploading to a shared instance.
- release — a faithful build: real version, vendored python modules,
--releaserender context.
If the user did not say, and they have just edited a template, use check.
Run it
ADCM_SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
bash "$ADCM_SCRIPTS/bootstrap.sh" # idempotent; skip if .adcm/venv already works
PY=.adcm/venv/bin/python
$PY "$ADCM_SCRIPTS/bundle_build.py" --check # check
$PY "$ADCM_SCRIPTS/bundle_build.py" --dev-version --skip-pymod # dev
$PY "$ADCM_SCRIPTS/bundle_build.py" --release # release
Read the discovery lines it prints first — the edition it chose, the submodules it skipped, the prototype file and version it found. Almost every surprise is explained there.
Judge the result
RENDER ERROR: file:line:is the primary feedback. Fix that file and line; do not work around it.YAML ERROR in rendered ...— line numbers refer to the output. Open.adcm/staging/<edition>/<path>at that line.- A submodule failure (exit 3) means no access to the private role repositories. Degrade
with
--check --stub-submodulesand say that the run was degraded — never conclude anything about YAML validity from a stubbed run. - A
python_mod_reqwarning means the archive is missing its vendored wheels. Fine for upload validation, wrong for a real deploy.
Report
The edition, the prototype name and the exact version built, the artifact path and size, and
any warning verbatim. If you used --dev-version, quote the full suffixed version — that is
what will appear on the instance.
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.
- 4d ago First seen · 54 lines · 19 tokens per session scan A ebfe5660e645
adcm-build is a command published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 19 tokens to every session and 576 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.