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/coolify-check-deployment)<a href="https://agentmods.dev/commands/alifanov/darkflow/coolify-check-deployment"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/coolify-check-deployment/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/coolify-check-deployment"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/coolify-check-deployment.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 | $0.00022 | $0.00500 |
| Opus 5.5 | $0.00009 | $0.00200 |
| Sonnet 5.5 | $0.00004 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
coolify-check-deployment 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 26d 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
Check the Coolify deployment status for this project: detect failed/red deploys and create a high-priority task. This is a passive health check — it does not auto-fix or trigger anything.
This command only looks at the deployment pipeline status. Runtime container errors, crashes, and OOM signals are covered by your observability tool (SigNoz/Datadog/Grafana) via /darkflow:observability-check, since container logs already ship there.
All Coolify data is fetched via the official coolify CLI (not an MCP server). Config lives at ~/.config/coolify/config.json.
Step 1 — Read project config
Load the project config (contract in .darkflow.d/claude.md → Project config). Uses: coolify_app, language.
Step 2 — Resolve the app UUID
If coolify_app is not set, list apps and find the UUID by name/project:
coolify app list
Step 3 — Check deployment status
Check the deployment history for failed/red deploys:
coolify app deployments list APP_UUID
- If the latest deployment is in a failed or error state: create a critical-priority task:
--source infra --priority critical --status proposed- Title: "Fix failed deployment: "
- Body: the deployment metadata + identified error. For details of the failed deploy:
coolify deploy get DEPLOYMENT_UUID --format pretty - Create with:
~/.darkflow/df task create --title "Fix failed deployment: <error summary>" \ --source infra --priority critical --status proposed --body "<deployment metadata + error>"
If the latest deployment succeeded, output: Coolify deployment OK — latest deploy succeeded.
Language for all tasks and output: the language value from .darkflow.d/state/config.json.
Guardrails
- Never trigger a new deployment — this is a passive check.
- Never expose secrets from deployment output — redact anything that looks like a key/token.
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.
- 26d ago Changed 34e762ed9289
- 1mo ago First seen · 53 lines · 22 tokens per session scan A 40d86e309b5f
coolify-check-deployment is a command published in the GitHub repository alifanov/darkflow (4 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 500 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
wasm-split
same flags, same behaviour, same output.
local
Command "local" from getsentry/toolkit, covering sentry local run, browser ui, endpoints, tail output and agent tracing.
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.
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.