Docs
Short, practical definitions for the terms openPrompting uses — plus the evidence model, freshness bands, commands, and links into the repository docs.
The words that matter.
- Agentic coding
- Using a coding agent — a model paired with tools, repository access, and an instruction file — to perform work inside a codebase.
- Model
- The AI performing reasoning and generation.
- Harness
- The coding tool around that model: repository access, instruction files, tools, permissions, and context management.
- Setup
- One model paired with one harness.
- Profile
- A user-defined role or name pointing to a setup, such as builder or reviewer.
- Task
- The type of work being performed — feature, bug, review, refactor, and so on.
- Prompting
- Supplying goals, context, constraints, and acceptance criteria so an agent can act reliably.
Prompting is not magic words.
Good prompting is generally less about phrasing and more about supplying an agent with useful material:
- Goals — what outcome is wanted.
- Context — files, symbols, and prior decisions that matter.
- Requirements — what must be true when the work is done.
- Constraints — what must not change.
- Acceptance criteria — how the outcome will be verified.
- Validation — the command or test that confirms success.
Evidence model
Each knowledge entry carries structured source metadata and a verification date. Every claim is classified into one of four evidence classes; entries also record last verified and per-source last checked dates.
Official
Supported directly by first-party provider or harness documentation.
Tested
Reproduced by maintainers with a procedure recorded in the entry.
Community
Useful practice without first-party confirmation.
Legacy
Historical or migration advice, not treated as the current default.
Freshness bands
The CLI’s doctor command reads last verified as a maintenance signal — a prompt to review an entry, not a correctness verdict:
- 0–60 days: current.
- 61–120 days: review suggested.
- 121+ days: stale.
This site shows the same band on every entry. The catalog currently holds 5 models, 7 harnesses, and 9 tasks.
Commands
openprompting helpopenprompting setupopenprompting guideopenprompting newopenprompting doctoropenprompting compareSuccessful commands exit 0; failures exit nonzero. Only setup writes project state; doctor is read-only.
Repository docs
The reference lives with the code. These links open the current files on GitHub:
- Command reference ↗Selectors, resolution rules, output, and exit behavior.
- Models, harnesses, setups, and profiles ↗How layers compose and how task routing resolves.
- Knowledge and evidence ↗Entry format, evidence classes, and sourcing rules.
- V1 contracts ↗Stable executable, commands, config schema, and vocabulary.
- Migration from pre-V1 builds ↗What changed and how to move forward.
- Release notes 1.1.2 ↗Package metadata and documentation patch.
- Release notes 1.1.1 ↗Documentation patch in the 1.1 line.
- Release notes 1.1.0 ↗Expanded catalog: models, harnesses, tasks.
- Changelog ↗All notable changes, SemVer.
- Contributing ↗Entry template, source checks, PR expectations.