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/antonbabenko/deliberation/grok-filesgit clone --depth 1 https://github.com/antonbabenko/deliberationWrote 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/antonbabenko/deliberation/grok-files)<a href="https://agentmods.dev/commands/antonbabenko/deliberation/grok-files"><img src="https://agentmods.dev/badge/commands/antonbabenko/deliberation/grok-files.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 | $0.00026 | $0.00992 |
| Opus 5 | $0.00013 | $0.00496 |
| Sonnet 5 | $0.00005 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
grok-files 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grok Files (storage cleanup)
List, prune, or gc the xAI files uploaded by the Grok bridge. Uploads are tagged with
the filename prefix deliberation-, so the remote-side cleanup ONLY ever targets
those - your own xAI files are never touched. Uploads also carry expires_after
(default 7 days) so they self-delete; this command is for pruning orphans early,
auditing what exists, or syncing the local SHA-256 cache with remote state.
Input
Sub-command + flags: $ARGUMENTS
(e.g. list, prune --older-than 24h, prune --older-than 7d --yes,
gc, gc --all-keys --force-local-prune)
Workflow
-
Resolve the admin script via this sequence:
- Glob
~/.claude/plugins/cache/*/deliberation/*/server/grok/files-admin.js; pick the highest-semver match. - Fall back to
${CLAUDE_PLUGIN_ROOT}/server/grok/files-admin.js. - If none exists, abort:
Error: deliberation plugin cache missing. Run /plugin install deliberation.
- Glob
-
Check auth: the script needs
XAI_API_KEYin the environment. If it is unset, tell the user toexport XAI_API_KEY=xai-...and stop (the script will error otherwise). -
Run the script with the user's sub-command (default
listwhen$ARGUMENTSis empty):node "<resolved files-admin.js>" $ARGUMENTSlist- prints total file count and everydeliberation-*upload (id, created, expires, name).prune --older-than <30m|24h|7d|seconds>- dry run by default; prints what it WOULD delete (remote files).prune --older-than <...> --yes- actually deletes the matched bridge-owned remote files.gc- syncs the local SHA-256 cache (~/.cache/deliberation/grok-files.json; Windows%LOCALAPPDATA%\deliberation\grok-files.json, override withDELIBERATION_CACHE) with remote state via one paginatedGET /v1/files. Prunes local rows whosefileIdis no longer on xAI. Default scope: currentXAI_API_KEY+XAI_API_BASErows only.gc --all-keys- widens the diff to foreign rows but leaves them when remote absence is ambiguous (the current key can't always see foreign files).gc --all-keys --force-local-prune- drops ambiguous foreign rows anyway. May orphan files on xAI under foreign accounts.
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 · 71 lines · 26 tokens per session scan A a131df1a9448
grok-files is a command published in the GitHub repository antonbabenko/deliberation (138 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 992 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 2026-08-30.
Other commands, from other repositories
ask
Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic — ask the council, council review…
result
Fetch, list, or cancel background council jobs started with --async.
status
Check connectivity and configuration status of all council providers.
setup
First-run wizard — pick AI providers, walk through CLI install + auth, verify each, save settings.
settings
Show or change which AI providers are enabled, the default, and the /ai:compare set.
codex-update
Install or update the upstream openai/codex-plugin-cc to the pinned tag.