coulomb/pqrst-practice
4
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
lightweight retrospective audit for agentic coding sessions on problem/quality/research/security/task-organization
12 commits 1 branch 0 tags 107 KiB
Find a file
tegwick e98ffab7e6 chore(consistency): refresh work-record index 
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ6oF1DtVDKcD1FCpvRVLx

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 272883@bnt-lap001
Assistant-Session: f40c8f53-fb65-4980-9d29-bcdb3dd946f7
2026-09-05 20:51:01 +02:00
history Consolidate PQRST drafts into spec v0.1; add prompt, intent, scope 2026-09-05 20:27:36 +02:00
spec Consolidate PQRST drafts into spec v0.1; add prompt, intent, scope 2026-09-05 20:27:36 +02:00
workplans repo.work.assign_missing_identifiers 2026-09-05 20:50:43 +02:00
.custodian-brief.md chore(consistency): sync task status from DB [auto] 2026-09-05 20:38:49 +02:00
.gitignore Register repo with State Hub under agents/practice 2026-09-05 20:33:29 +02:00
.repo-classification.yaml Add repo classification and work-record index 2026-09-05 20:34:01 +02:00
AGENTS.md Complete PQRST-WP-0001: bootstrap State Hub integration 2026-09-05 20:38:30 +02:00
INTENT.md Consolidate PQRST drafts into spec v0.1; add prompt, intent, scope 2026-09-05 20:27:36 +02:00
PqrstPrompt.md Consolidate PQRST drafts into spec v0.1; add prompt, intent, scope 2026-09-05 20:27:36 +02:00
README.md Complete PQRST-WP-0001: bootstrap State Hub integration 2026-09-05 20:38:30 +02:00
SCOPE.md Complete PQRST-WP-0001: bootstrap State Hub integration 2026-09-05 20:38:30 +02:00
WORK-RECORDS.md chore(consistency): refresh work-record index 2026-09-05 20:51:01 +02:00

README.md

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 — Problem, Quality, Research, Security, Task 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 — paste it, done
Understand the model spec/PqrstEstimationPractice.md (v0.1)
Know why it exists, and what it must not become INTENT.md
Know what belongs in this repo SCOPE.md
Work in this repo as an agent AGENTS.md

What a record looks like

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.