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 skills/raphaelmansuy/edgequake/makefile-dev-workflownpx skills add raphaelmansuy/edgequake --skill makefile-dev-workflowgit clone --depth 1 https://github.com/raphaelmansuy/edgequakeWhat 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 | $0.00048 | $0.02248 |
| Opus 5 | $0.00024 | $0.01124 |
| Sonnet 5 | $0.00010 | $0.00450 |
| Haiku 4.5 | $0.00005 | $0.00225 |
Grade A, and why
makefile-dev-workflow 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Makefile Development Workflow
When to use
Use this skill when you need to:
- Start development services (database, backend API, frontend)
- Stop services cleanly
- Run end-to-end tests with Playwright
- Check service health status
- Build and deploy applications
- Clean build artifacts
- Manage the full development stack with a single command
Core concepts
The repository includes a unified Makefile (at repo root) that wraps complex shell commands into simple targets. This replaces scattered docker-compose commands and cargo/npm invocations with a consistent interface.
Key directories
edgequake/: Rust backend API (port 8080)edgequake_webui/: Next.js frontend (port 3000)edgequake/docker/: Docker configuration with docker-compose.yml (contains PostgreSQL + pgvector + Apache AGE)
Quick start commands
Start full development stack (all services)
make dev
Starts PostgreSQL, Rust backend, and Next.js frontend in parallel. Displays URLs for all services.
Start full stack with local Langfuse v4
make dev-langfuse # foreground
make dev-bg-langfuse # background (agentic)
make spec124-langfuse-e2e # one-command live Settings + sessions (needs Ollama or OPENAI_API_KEY)
Starts isolated Langfuse (UI http://localhost:3310) plus the EdgeQuake stack, and injects Compose init keys into the backend (overrides Cloud/placeholder keys in .env). make stop does not tear Langfuse down (make langfuse-down).
Stop all services
make stop
Kills all running processes and stops Docker containers gracefully.
Check service status
make status
Shows health of backend, frontend, and database with actual health checks and endpoints.
Service-specific commands
Database management
make db-start # Start PostgreSQL container (port 5432)
make db-stop # Stop PostgreSQL gracefully
make db-logs # View PostgreSQL logs in real-time
make db-shell # Open psql shell into the database
make db-reset # DANGER: Delete all data and reinitialize database
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 · 429 lines · 48 tokens per session scan A 4d78c4fc350b
makefile-dev-workflow is a skill published in the GitHub repository raphaelmansuy/edgequake (2,080 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 2,248 once invoked, about $0.0002 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 skills, from other repositories
jurisd-research
Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…
harness-node-splitter
Split a workflow description into constrained harness nodes using the chapter's rule "nodes differ by tool surface, not by prompt." Given candidate operations each with a declared tool set, merge the ones whose tool surfaces overlap >= 80% (prompt variations of one role) and split the ones with distinct tool surfaces…
draft-tool-trust-verifier
Establish trust in a tool by verification, not by its self-description. Flags marketing-gamed tool descriptions ("industry-leading", "trusted by Fortune 500"), requires structured testable capabilities instead of free-text claims, tracks a performance-based trust score (neutral start, successes up, failures and slow…
dual-graph-router
Route an incoming request to the VERTICAL knowledge graph (what the agent knows — a single relationship/temporal traversal), the HORIZONTAL workflow graph (how the agent acts — a decomposed multi-step process), BOTH (a workflow whose nodes query the knowledge graph and write results back), or UNROUTABLE (neither fits…
eight-pillar-readiness-map
Map an agentic-graph system's current capabilities across the eight pillars of Agentic GraphRAG Ch2 (knowledge representation, memory, reasoning, planning, tool orchestration, structured output, self-evolution, optimization), respect the chapter's layering (each pillar depends on the ones before it), flag dependency…
cost-performance-scorer
Score a multi-model routing policy on cost versus quality using the two metrics that actually decide selective intelligence: cost per successful completion (not cost per token) and a per-node quality parity threshold with domain-specific failure weights. Wraps a NodeInvocation log, computes cost-per-success and p95…