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-validategit 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-validate)<a href="https://agentmods.dev/commands/arenadata/adcm-agent/adcm-validate"><img src="https://agentmods.dev/badge/commands/arenadata/adcm-agent/adcm-validate.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 | $0.00017 | $0.00537 |
| Opus 5 | $0.00009 | $0.00269 |
| Sonnet 5 | $0.00003 | $0.00107 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
adcm-validate 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 3d 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
Validate the bundle change in this repository. Scope: $ARGUMENTS
Load the adcm-bundle-validate skill — it owns the layers, the error mapping and the version-collision rules.
Always rebuild first
Even for a one-line change. It takes a second and it guarantees you are testing what you edited, not the last archive that happened to be lying around.
ADCM_SCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
PY=.adcm/venv/bin/python
$PY "$ADCM_SCRIPTS/bundle_build.py" --dev-version --skip-pymod
$PY "$ADCM_SCRIPTS/bundle_check.py"
Stop here for static scope, or if the static run fails — an upload cannot tell you anything useful about a file that does not parse.
Then let ADCM judge it
Requires a configured instance (/adcm-connect if not).
python3 "$ADCM_SCRIPTS/adcmctl.py" upload
The upload response is the real test: ADCM validates every prototype, config field, action
state machine and constraint. UPLOAD REJECTED with validation text is a bundle defect
and is exactly the result you asked for.
Map errors back to the source
ADCM names the rendered path. Open .adcm/staging/<edition>/<path> at the reported line,
then find the corresponding place in the .j2 source — and in auto_bump/raw/ if the file
is generated. Do not count Jinja blocks by eye.
Handle a version collision correctly
HTTP 409 means that version is already on the instance. If --dev-version was used this
should not happen; if it does, the version belongs to somebody else. Rebuild with a fresh
--dev-version. Use upload --replace only for a version this checkout uploaded — the
tool checks, and refuses otherwise. Never delete a bundle to clear a 409.
Report
- build — version and edition actually built
- static — per-layer counts, PASS/FAIL, and every
file:lineverbatim - upload — the bundle id, or the first server validation error quoted exactly, plus the source line it maps to
Never paraphrase a validation error.
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.
- 3d ago First seen · 60 lines · 17 tokens per session scan A cd603f6ab1fc
adcm-validate is a command published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 17 tokens to every session and 537 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.