tegwick
883409665f
HF-WP-0005. The prompts used to drive work across HelixForge repositories existed only as text pasted between sessions. They are now Canned Prompt Format v0.2 packages with declared inputs, parameters and output contracts. Seven packages: repo-orient (merging "what is this repo about" with "what should we do now" as a `depth` parameter), repo-register, repo-advance, commit-sync, scope-audit, gap-workplan, session-close. "Go on implement, please" is deliberately not packaged. It is conversational continuation with no contract to declare, and packaging it would produce an artifact whose only content is the word "continue". Every one of these prompts assumed the operator's setup — the State Hub is a read model, workplans originate as files and are never registered by hand, a session closes with a progress event. That assumption is what made them personal rather than reusable. helix/custodian-conventions states those rules once as a fragment composed by every package, so they are versioned, improvable in one place, and present for an agent that has never seen this fleet. helix/commit-sync-routine exists for a narrower reason. repo-advance first composed the whole commit-sync package, which itself composes the conventions, so the rendered prompt carried the conventions block twice — CPF inclusion does not deduplicate, and a diamond dependency renders shared content once per path. Factoring the routine out removes the diamond and is a better factoring regardless. Recorded upstream as canned-prompts CANP-WP-0004-T03. helix/session-close composes practice/pqrst-estimate, so the canonical PQRST block is embedded verbatim. hall-of-helix CLOSING.md says the canonical prompt still governs when you have no pqrst-practice checkout, without saying how it reaches you; this is how. evals/pqrst-embedded.yaml fails if the canonical text stops being embedded verbatim, rather than letting the package quietly become a paraphrase. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Bjefh8NUiEiahN4JLwoSKM Assistant: claude-code Assistant-Model: opus Assistant-Process: 388925@bnt-lap001 Assistant-Session: 3507023f-e0fd-4a1e-9d90-a0d4217d1502
26 lines
1.1 KiB
YAML
26 lines
1.1 KiB
YAML
schema: canned-prompts/eval-rubric/v0.1
|
|
name: pqrst-embedded-verbatim
|
|
description: >
|
|
The point of composing practice/pqrst-estimate is that closing a session needs
|
|
no pqrst-practice checkout. If the canonical text stops being embedded
|
|
verbatim, this package silently becomes a paraphrase — the failure that
|
|
practice/pqrst-estimate itself already had once.
|
|
example: examples/basic.yaml
|
|
|
|
render:
|
|
- resolves_all: true
|
|
- not_contains: "{{"
|
|
- contains: "P — Main Problem:"
|
|
- contains: "S — Security and Credentials:"
|
|
- contains: "must sum to exactly 100"
|
|
- contains: "Signature: P<int> Q<int> R<int> S<int> T<int>"
|
|
- contains: "S may legitimately be 0%"
|
|
- contains: "## Operating conventions"
|
|
- contains: "keep the invalid record and say so in the seat"
|
|
|
|
output:
|
|
criteria:
|
|
- The PQRST record validates, or is kept invalid with the failure stated.
|
|
- The seat carries the signature in frontmatter and the full record in a section.
|
|
- The estimate covers the substantive session, excluding the closing ritual.
|
|
- The seat reads as a perspective, not a status report.
|