# pqrst-practice

A lightweight retrospective audit for closing agentic coding sessions: a forced
100% allocation of a session's effective engineering effort across five stable
dimensions — **P**roblem, **Q**uality, **R**esearch, **S**ecurity, **T**ask
organization.

> Where did the effective engineering effort of this session actually go?

## Start here

| I want to… | Read |
| --- | --- |
| Close a session right now | [`PqrstPrompt.md`](PqrstPrompt.md) — paste it, done |
| Understand the model | [`spec/PqrstEstimationPractice.md`](spec/PqrstEstimationPractice.md) (v0.1) |
| Know why it exists, and what it must not become | [`INTENT.md`](INTENT.md) |
| Know what belongs in this repo | [`SCOPE.md`](SCOPE.md) |
| Work in this repo as an agent | [`AGENTS.md`](AGENTS.md) |

## What a record looks like

```text
PQRST-Estimate
P: 25%
Q: 15%
R: 45%
S: 0%
T: 15%
Sum: 100%
Confidence: medium
Signature: P25 Q15 R45 S0 T15
Dominant factors: Existing auth middleware was undocumented and contradicted the
README, so most attention went to reconstructing the request path before
changing behavior.
```

The numbers are the index. The `Dominant factors` sentence is the content — a
signature stored without it is not auditable.

## What this is not

Not a productivity score, not telemetry, not a planning target. There is no good
profile: an exploration session is R-heavy, a hardening session Q-heavy, a
credential integration S-heavy. The practice fails the moment anyone tries to
score well on it.

This repository defines the practice and supplies the prompt. Collectors,
validators, dashboards, and record storage belong elsewhere — see
[`SCOPE.md`](SCOPE.md).