Plugin Claude Code
Multi-model consensus review for specs and plans before execution.
Plugin Claude Code
Multi-model consensus review for specs and plans before execution.
Plugin Claude Code
Multi-model consensus review for specs and plans — panels haiku + sonnet tiers per topic, opus juror on disagreements, fail-closed verdict gate.
Skill Claude CodeCodex
Use when a spec or plan needs review before execution begins - "review my spec", "is this plan ready to execute", "check this before I build it", "second opinion on this plan" - and specifically before writing-plans (spec mode) or before subagent-driven-development (plan mode). Reviews specs and plans, not code.…
Agent
Use this file when dispatching the alignment reviewer agent (fast tier and standard tier). The coordinator replaces [ARTIFACTCONTENT], [MODELABEL], [SUPPLEMENTARYCONTEXT], and [PROJECTCONTEXT] before dispatching.
Agent
Use this file when dispatching the completeness reviewer agent (haiku tier and sonnet tier). The coordinator replaces [ARTIFACTCONTENT], [MODELABEL], and [PROJECTCONTEXT] before dispatching.
Agent
Use this file when dispatching the risk reviewer agent (haiku tier and sonnet tier). The coordinator replaces [ARTIFACTCONTENT], [MODELABEL], and [PROJECTCONTEXT] before dispatching.
Agent
Use this file ONLY when the coordinator has detected contested findings. Replace [ALLSIXREPORTS] and [CONTESTEDLIST] before dispatching. Model: always opus.
Plugin Claude Code
House-style technical writing skills: design docs, decisions, changelogs, runbooks, tracker issues, and prose review.
Plugin Claude Code
House-style technical writing: a core style and truth skill plus specialized skills for design docs, decisions, changelogs, runbooks, tracker issues, and prose review.
Agent
Read-only grounding agent for documentation campaigns. Use to ground one document of a legacy campaign against the code at HEAD, to reground a stale document, or to verify what a system actually does before it is written down. Produces prose and findings; never edits code.
Agent
Fresh-eyes reviewer for technical documents. Use after writing or editing any document that must meet the house writing doctrine, when a review must not trust the author's own account, or when a digest-bound verdict is needed before shipping. Reviews prose; never edits it.
Command
Launch a legacy documentation campaign for a codebase or directory.
Command
Run the fresh-eyes house review on one or more documents.
Skill Claude CodeCodex
Use when a business process, workflow, lifecycle, or interaction between systems needs a diagram - a flow that prose serializes badly, a state machine, a message sequence, an enterprise process map - or when drawing the process documentation of a legacy campaign. Encodes diagrams-as-source, the notation ladder from…
Skill Claude CodeCodex
Use when documenting an HTTP API, message payloads, queue contracts, DTOs, file formats, or webhooks - or when writing the api-reference of a legacy campaign, or when callers keep asking what a field means or which errors an endpoint returns. Encodes the four detail levels, the DTO-first catalog, wire types with…
Skill Claude CodeCodex
Use when documenting an existing codebase whose documentation is missing, stale, or untrusted - an inherited system, a legacy application, a repo where the docs lie - or when regrounding a documentation tree against the code, or when someone asks what a system actually does. Encodes the survey-first inventory, the…
Skill Claude CodeCodex
Use when a decision needs recording - an ADR, a decision log entry, or when someone asks to write down why something was chosen, rejected, or superseded. Encodes the ADR and decision-log formats. Use whenever a choice was made that would otherwise live only in chat, even if nobody says "ADR".
Skill Claude CodeCodex
Use when reviewing, rewriting, or editing someone else's technical text, when writing a review report on a document, or as the final check before delivering any document. Encodes the severity mapping, the findings format, the what-not-to-flag list, and the delivery checklist. Use before any document ships, even when…
Skill Claude CodeCodex
Use when writing, restructuring, or revising any technical document - specs, design docs, READMEs, reference documentation, plans, reports - or any prose that must survive being read twice by someone in a hurry. Encodes the house style, the truth and sourcing rules, and the banned-constructions list. Use whenever you…
Skill Claude CodeCodex
Use when writing a changelog entry, release notes, or a "what shipped" summary after completing work. Encodes the entry shape, the handover template, and the honesty conventions. Use after shipping meaningful work, even if the user just says "summarize what we did".
Skill Claude CodeCodex
Use when writing a proposal, RFC, design document, spec, or migration plan - anything that argues for a change, records a design, or asks readers for input on one. Encodes the proposal skeleton, the Why & What decision box, and the completeness checks. Use whenever a change needs arguing or scoping in writing, even if…
Skill Claude CodeCodex
Use when writing or refining tracker items - epics, stories, tasks, bug reports, spikes, or acceptance criteria - or when turning a discussion, review finding, or plan into tickets. Encodes the survives-without-you test, the issue-type glossary, and the story and bug skeletons. Use whenever work is written into a…
Skill Claude CodeCodex
Use when writing a postmortem, incident report, or root-cause analysis after an outage, a defect that reached users, a data issue, or a near miss - or when turning an incident channel, alert log, or war-room thread into a durable document. Encodes the blameless framing, the evidence-only timeline, contributing…
Skill Claude CodeCodex
Use when writing operational documentation - runbooks, setup guides, release procedures, migration guides, deprecation guides, troubleshooting entries, or any ordered procedure someone will execute under time pressure. Encodes the runbook skeleton, the risk legend, the symptom-first troubleshooting format, and the…