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.
git clone --depth 1 https://github.com/alifanov/darkflowWrote 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/alifanov/darkflow/mailbox-check)<a href="https://agentmods.dev/commands/alifanov/darkflow/mailbox-check"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/mailbox-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/alifanov/darkflow/mailbox-check"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/mailbox-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.01280 |
| Opus 5.5 | $0.00009 | $0.00512 |
| Sonnet 5.5 | $0.00005 | $0.00256 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
mailbox-check 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note — cheap pre-flight. The dispatcher (
darkflow-run.sh) runs a read-only IMAP unseen-count (fetch.py --count) and adf task listfor approved reply tasks before launching this agent. If there's no new mail and no reply pending, it skips this agent entirely — so on a quiet inbox you are not invoked. When you are invoked there is real work (new mail and/or replies to send); proceed with the full steps below.
Step 1 — Read config
Load the project config (contract in .darkflow.d/claude.md → Project config). Uses: language, branch, mergeStrategy.
Load mailbox credentials from .env (the project's main env; .env.darkflow is a legacy fallback):
set -a; [ -f .env.darkflow ] && source .env.darkflow; [ -f .env ] && source .env; set +a
If MAILBOX_IMAP_HOST is empty after sourcing — stop and print "mailbox not configured — add MAILBOX_IMAP_* vars to .env".
Step 2 — Send approved replies
Find all open tasks with status:approved, source:mailbox, action:reply:
~/.darkflow/df task list --status approved --source mailbox --action reply --state open
For each such task:
-
Extract email metadata from the task body (look for the structured block added in Step 4):
- To — value of
From:field in the task body (reply goes back to the sender) - Subject —
Re:+ original subject fromSubject:field - Message-ID — value of
Message-ID:field for threading
- To — value of
-
Check if there are any human comments on the task. If yes — include them as the reply body context (the human may have added instructions or draft text). If not — write a polite, short acknowledgement in
languagethat the message was received and is being handled. -
Write the reply body to a temp file:
cat > /tmp/darkflow_reply_$number.txt << 'EOF' <reply text here> EOF -
Send the reply:
python3 ~/.darkflow/mailbox/send.py \ --to "<From address from task>" \ --subject "Re: <original subject>" \ --in-reply-to "<message-id from task>" \ --body-file /tmp/darkflow_reply_$number.txt
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.
- 1mo ago First seen · 126 lines · 23 tokens per session scan A 7aa57ac0c843
mailbox-check is a command published in the GitHub repository alifanov/darkflow (4 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,280 once invoked, about $0.0001 per session on Opus 5.5. 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
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
auth
Bare sentry auth logs in when you're logged out and shows status when you're already authenticated. sentry auth login always starts the login flow.
debug-files
Command "debug-files" from getsentry/toolkit, covering notes on find and important notes.
react-native
Command "react-native" from getsentry/toolkit, covering xcode build step (react-native xcode) and important notes.
amp-download
Command "amp-download" from agentmessaging/claude-plugin, covering /amp-download, usage, arguments, options and examples.
release
A typical CI release creates the release, associates commits, finalizes it, and records a deploy. The sentry release create examples above show the full sequence.