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/wrannaman/agentic-engineering/setupnpx skills add wrannaman/agentic-engineering --skill setupgit clone --depth 1 https://github.com/wrannaman/agentic-engineeringWhat 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 | $0.00033 | $0.03489 |
| Opus 5 | $0.00016 | $0.01744 |
| Sonnet 5 | $0.00007 | $0.00698 |
| Haiku 4.5 | $0.00003 | $0.00349 |
Grade A, and why
setup scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Verify: `curl -H "Authorization: Bearer $TOKEN" $URL/health` How it starts
The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
From zero to working agentic engineering in one session.
Walk a new user through the entire stack: detect their codebase, deploy or connect to a KB server, write project-specific configuration, optionally seed the KB, and verify it all works.
The agent does the work. The user answers questions and confirms.
Process
Step 0: Quick or Full?
Before anything else, ask ONE question:
What are you looking to do?
1. Just try it out — get a local KB running with the example docs in 2 minutes
2. Set this up for real — connect to my codebase, configure everything properly
If "just try it out" (the quick path):
Skip everything and do this:
cd apps/kb-server
python -m venv .venv && source .venv/bin/activate
pip install -e .
REPOS="kb:../../examples/seed-kb" python -m src.server &
Then configure the agent to connect:
# For Claude Code:
claude mcp add --transport http kb http://localhost:8080/mcp
Done. Say:
KB server running at http://localhost:8080 with 5 example docs.
Try: list_documents() to see what's in the KB.
When you're ready to add your own docs, just drop markdown files into
examples/seed-kb/ (or any folder) and hit localhost:8080/api/sync.
Run /setup again and pick option 2 when you want the full configuration.
That's the entire quick path. No more questions. They're up and running.
If "set this up for real": Continue to Step 1.
Step 1: Where Am I?
First, figure out if the user is in the agentic-eng repo or in their own project:
# Check if we're in the agentic-eng repo itself
ls apps/kb-server/src/server.py 2>/dev/null && ls skills/core/plan/SKILL.md 2>/dev/null
If we're in the agentic-eng repo:
They just cloned it. They need to:
- Start the KB server (done in Step 0 quick path, or Step 2 full path)
- Install skills into their agent
- Then go to their actual project and configure it
It looks like you're in the agentic-eng repo itself — not a project you want to configure.
Let's get you set up:
1. ✅ Start the KB server (done — or we'll do it in Step 2)
2. Install skills: cd skills && ./install.sh
3. Go to your project: cd /path/to/your/project
4. Run /setup again from there to configure your project
What's the path to the project you want to configure?
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.
- yesterday First seen · 435 lines · 33 tokens per session scan A 45b22edc7654
setup is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 3,489 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…