knowledge base · ai coding tools

AI coding tools, decoded.

What Claude Code, OpenCode, OMP, OMO, herdr and the models behind them really are, how they differ, when to use each, and how to keep the result safe.

$ click a card for details · ctrl+k to search

learning map

Topics are laid out by level, from foundations to advanced. Arrows point from a prerequisite to what builds on it. Select a topic to preview it, or follow the highlighted next step.

Your next step

0 of 9 studied

start this topic

01 Foundations

The ideas everything else builds on.

02 Practitioner

Apply the controls and make them work in practice.

03 Advanced

Design, scale and operate at depth.

studied
ready to study
prerequisites missing
arrows go from a prerequisite to what builds on it

from understanding to trusting

Understand the tools, choose by task, drive them with good context, and verify everything. Each chip opens the matching topic.

01understand
what these tools really are
the spectrum from autocomplete to agents model, harness and provider
gate: you can say which layer a tool belongs to and how much autonomy fits the task
02choose
the right tool and model for the job
Claude Code, OpenCode, OMP, OMO, herdr frontier, cheap and open models a decision guide
gate: tool and model chosen by task and risk, not by habit
03drive
give context, split the work
instructions, plans, skills and small tasks worktrees and many agents
gate: each task is small, specified and has a check that decides success
04verify
trust only what you can check
tests, diffs and CI gates permissions, sandboxes and injectionhuman review before merge
gate: nothing merges unverified, and the agent cannot reach what it should not

topics

The vibecoding spectrum

"Vibecoding" names a way of working, not a tool: you describe what you want and steer by results instead of reading every line. It is excellent for some jobs and reckless for others, and knowing which is the skill.

concept· stage: understand

Model, harness and provider

A coding agent is not just a model. It is a model plus a harness (the program that gives it tools, context and rules) reached through a provider. Most confusion in this field comes from mixing the three.

concept· stage: understand

Coding agents compared

Some of these are harnesses, some are plugins that sit on a harness, and some are not agents at all. Sorting them into the right layer explains most of the differences.

practice· stage: choose

Choosing a model: frontier, cheap and open

The best model for a task is the cheapest one that passes your tests. Price, speed and privacy matter as much as benchmark scores, and DeepSeek-style models make that trade-off concrete.

practice· stage: choose

When to use what

Start from the task and its risk, not from the tool you like. A small decision table covers most days.

concept· stage: choose

Context engineering for coding agents

Agents do not remember your project; they read what you put in front of them. Good results come from what the model sees: clear instructions, the right files, a plan, and tasks small enough to verify.

technique· stage: drive

Orchestration and parallel agents

One agent is a pair programmer. Several agents are a small team, and a team needs isolation, a way to see who is doing what, and a human who reviews the merges.

practice· stage: drive

The verification loop

Generated code looks confident whether it is right or wrong. The only reliable defense is a loop that checks it: tests that decide, a diff you read, and gates that run no matter who wrote the code.

technique· stage: verify

Securing the agent itself

A coding agent reads untrusted text and runs commands with your permissions. That combination is exactly what prompt injection and supply-chain attacks exploit, so the agent needs the same controls as any powerful automation.

technique· stage: verify