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/update-config)<a href="https://agentmods.dev/commands/alifanov/darkflow/update-config"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/update-config/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/update-config"><img src="https://agentmods.dev/badge/commands/alifanov/darkflow/update-config.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 | $0.00000 | $0.00691 |
| Opus 5.5 | $0.00000 | $0.00276 |
| Sonnet 5.5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
update-config 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 18d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/darkflow:update-config ← interactive (ask for new values)
/darkflow:update-config lang=Russian
/darkflow:update-config branch=develop
/darkflow:update-config lang=Russian branch=develop
Step 1 — Read current settings
Run bash ~/.darkflow/get-config.sh to pull the latest project settings from the Web UI and refresh the project config at .darkflow.d/state/config.json (silently falls back to cache if the server is unreachable).
Read .darkflow.d/state/config.json from the project root. Extract language and branch values. If the file is missing, abort with an error.
Step 2 — Determine new values
Parse any lang and branch arguments passed to the command.
For any value not provided as an argument, ask the user interactively:
- Language: current value shown as default; accept free text (e.g. English, Russian, Spanish)
- Main branch: current value shown as default; accept free text (e.g. main, master, develop)
If the user presses Enter without input, keep the current value unchanged.
Step 3 — Update the settings in the Web UI
language and branch live in the Web UI database; .darkflow.d/state/config.json is only a cache that get-config.sh overwrites. Ask the user to change the values in the Web UI, then refresh the cache:
bash ~/.darkflow/get-config.sh
Step 4 — Update .darkflow.d/claude.md
Read .darkflow.d/claude.md. Update the main-branch line in-place:
# macOS
sed -i '' "s/^\*\*Main branch:\*\* .*/\*\*Main branch:\*\* \`<NEW_BRANCH>\`/" .darkflow.d/claude.md
# Linux
sed -i "s/^\*\*Main branch:\*\* .*/\*\*Main branch:\*\* \`<NEW_BRANCH>\`/" .darkflow.d/claude.md
Also update any line that reads → PR → merge to <old-branch> or push directly to \`to use<NEW_BRANCH>`.
Step 5 — Commit and push
Stage and commit the changed files:
git add .darkflow.d/claude.md
git commit -m "chore: update darkflow config (lang=<NEW_LANG>, branch=<NEW_BRANCH>)"
git push
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.
- 18d ago Changed · -8 lines a714b81a72b0
- 1mo ago First seen · 83 lines · 0 tokens per session scan A 9623352c9de3
update-config is a command published in the GitHub repository alifanov/darkflow (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 691 tokens. 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
revisit
Intake recorded each item below as blocked: something had to happen first. Work lands in parallel, so a blocker can be resolved, superseded or made irrelevant while its issue is still open, and an item can stay blocked long after it could move. Judge, for each item, whether it still looks blocked now. You don't…
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.
issue-tracker
Intelligent issue management and project coordination with ruv-swarm integration for automated tracking, progress monitoring, and team coordination.
github-modes
This document describes all GitHub integration modes available in Claude-Flow with ruv-swarm coordination. Each mode is optimized for specific GitHub workflows and includes batch tool integration for maximum efficiency.
next
Suggest the most likely next workflow action based on current context.