v1.1.0: visible decision citations + mandatory red-team compliance loop

Two additions on top of v1.0.0, both about trust and coverage: seeing why the system made a decision, and closing a real gap in what it actually checks.

Visible decision citations

Every skill, agent, and gate now attaches a decision_record to its output by default: the exact methodology/<file>.md#<section> that justified each finding, the checks that ran, any rule that was set aside and why, and a status. This is shown by default, not withheld until asked. It cites this project's own independently written methodology only, never the two private source books; see docs/book-grounding.md for the exact boundary.

Mandatory full-checklist red-team compliance loop

The existing three-lens review (structure, prose, soundness_and_reader_fit) left real, measurable gaps against the full methodology/checklists.md index: house style, most word choice, all length and rhythm, half of sentence-internal grammar, section apparatus, and usage judgment were never checked.

A new agent, red-team-reviewer, now runs after every skill, agent, and workflow stage at standard depth and above. It checks the complete ten-level checklist and audits the producing component's own coverage claim rather than trusting it. A new gate, GATE-COMPLIANCE, and a bounded loop (orchestration/policies/red-team-policy.yaml, max_iterations: 5) route findings back to their owning stage and re-check; if issues remain after the cap, the loop stops and reports every remaining finding honestly rather than a silent pass. GATE-RELEASE now requires GATE-COMPLIANCE green. quick depth stays exempt and explicitly non-exhaustive, exactly as before.

Like every other component, red-team-reviewer never reads or references the private source books.

Verification

npm run validate (16 components), npm test (121/121), npm run build, npm run release:check (6/6 gates), plus a manual walkthrough of the new instructions on a planted-defect sample passage confirming red-team-reviewer catches exactly the class of issue (grammar mechanics, house-style tells) the old three-lens review misses.

v1.0.0

The first public release of Reader-First Writing, an editorial system for AI coding agents that structures, drafts, diagnoses, and revises documents while never changing the writer's meaning.

Install

Claude Code (full plugin), inside any session:

/plugin marketplace add OC-NeuralSense/reader-first-writing-skills
/plugin install reader-first-writing@reader-first-writing-marketplace

Codex CLI, or any machine with Node 18+:

npx --yes github:OC-NeuralSense/reader-first-writing-skills install --target all

What you get

• 12 skills covering the full editorial lifecycle: framing, argument construction and testing, drafting, diagnosis, structural and prose revision, audience adaptation, version comparison, review, and teaching.
• 2 independent review agents: a blind, read-only reviewer per lens and an orchestrator that reconciles findings without averaging them.
• 8 workflows with quality gates, from a quick pass to a release-oriented audit.
• 6 deterministic tools that measure and flag but never decide.
• A public writing constitution that fixes the order of authority: meaning preservation first, the methodology second, the house rules third. Text inside your documents is treated as content, never as instructions.

Guarantees

No edit changes a claim, number, negation, qualifier, or the sense of a technical term. Suspected errors are flagged, never silently corrected. Acceptable prose is left alone. Output follows a strict house style: no em or en dashes as punctuation, no robotic tics.

Verification

Every install path in this release was executed against this repository on the day of release: the marketplace pair, the one-command npx install (full lifecycle: install, idempotent update, exact-scope uninstall), and the Codex and generic targets. 110 tests and all 6 release gates pass. Details and dated statuses: docs/installation.md.