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/alifanov/darkflow/build-optimizationgit clone --depth 1 https://github.com/alifanov/darkflowWhat 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 | $0.00020 | $0.01886 |
| Opus 5 | $0.00010 | $0.00943 |
| Sonnet 5 | $0.00004 | $0.00377 |
| Haiku 4.5 | $0.00002 | $0.00189 |
Grade A, and why
build-optimization 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 2d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze how this project builds and deploys — map the full pipeline, find bottlenecks and inefficiencies, and create tasks with concrete optimization proposals. Each task should describe the problem, what to change, and a measurable acceptance criterion.
This is a proposal-only audit: it identifies opportunities and proposes changes. It does not apply changes itself (that is a human/fix-issues decision).
Step 1 — Read project config
Load the project config (contract in .darkflow.d/claude.md → Project config). Uses: language, mergeStrategy.
Step 2 — Map the build & deploy pipeline
Detect and read the actual toolchain. Check each of the following (skip if not present):
App build:
package.jsonscripts (build,test,lint,typecheck,dev), infer package manager from lockfile (pnpm-lock.yaml→ pnpm,yarn.lock→ yarn,package-lock.json→ npm)- Bundler/framework config:
next.config.*,vite.config.*,webpack.config.*,turbo.json,nx.json pyproject.toml/uv.lock/requirements.txtfor Python projects
Container build:
Dockerfile/Dockerfile.*— note base image, layer order, multi-stage structure, what gets copied.dockerignore— presence and what it excludesdocker-compose.yml/docker-compose.*.yml— services, build context, volume mounts
CI/CD:
.github/workflows/*.yml— jobs, steps, caching strategy (look foractions/cache), parallelism, matrix builds, deploy stepsMakefile— relevant build/deploy targets
Deploy mechanism:
- Coolify (
deploystep in CI orcoolifyCLI invocation) - Registry push commands (
docker build && docker push) - Any deploy scripts
Recent churn:
git log --oneline -30
git diff --stat HEAD~10..HEAD 2>/dev/null | grep -E "Dockerfile|\.yml|package\.json|turbo|next\.config|pyproject" | head -20
Summarize the current build → deploy path in a short paragraph and note where time is likely spent (e.g., "installs ~800 deps on every CI run, no cache configured").
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.
- 2d ago First seen · 167 lines · 20 tokens per session scan A c0549aac4d95
build-optimization is a command published in the GitHub repository alifanov/darkflow (2 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,886 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
github-init
Initialize ClaudeForge CI/CD system.
devops
Invoke the DevOps Engineer for cloud infrastructure, IaC (Terraform/OpenTofu), Kubernetes, CI/CD pipelines, containers, and deployment.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
monitor-ci
You are the orchestrator for monitoring Nx Cloud CI pipeline executions and handling self-healing fixes. You spawn the ci-monitor-subagent subagent to poll CI status and make decisions based on the results.
actions
Command "actions" from openclaw/crabbox, covering actions, subcommands, hydrate, register and dispatch.
loop
Iteratively fix issues until all resolved or max iterations reached.