grimoire

Plugin grimoire from marketplace applefeld in SApplefeld/claude-kit. Commands read from the repo's manifest — 1 month ago.

Skills (24)

• brainstorming

  Collaborative design conversation for any new feature, project, or non-trivial change. Use when I want to think through a problem before building. Phrases like 'let's think through', 'help me design', 'spec this out', 'how should we approach', or any substantial new effort without an existing spec.

• branch-hygiene

  Use to clean up local branches and worktrees left over after Branch-and-PR efforts, or when the SessionStart nudge flags reapable OR stranded branches. Triggers: branch cleanup, reap or prune merged branches, recover stranded post-merge commits, leftover or stale local branches, worktree cleanup, to

• consult

  Convene one fresh-context judge to rule on a question this session cannot settle: the consultant agent at every floor shape but the design stop, whose judge executing-work convenes. Use mid-execution at a second failed attempt at the same problem, any BLOCKED that turns on a decision, a debugging de

• coordinator

  Use when taking or resuming the machine-coordinator seat, running a coordination loop over several live sessions, or coordinating the machine's sessions across repos. Triggers: claiming the coordinator role, a reconciliation pass over the live roster and the machine's session registry, cross-repo se

• csharp-style

  My C# house style. Use whenever writing or modifying ANY C# code: new services, handlers, helpers, MediatR notifications, models, DI registration, or refactoring existing C#. Signature traits: #region organization, section comments ending in periods, grouped fields with label comments. Trigger on an

• curating-docs

  Use during finishing-work when a plan reaches Complete, when a new plan is written that should be indexed and cross-referenced, or when asked to tidy, retrofit, or reorganize a project's docs/ folder. Symptoms: completed plans piling up in docs/plans/, a backlog doc that only grows, plans that never

• design-council

  Convene a read-only, multi-lens design council to pressure-test competing approaches at a genuine architecture fork. Offered by the brainstorming skill when a decision is material and hard to reverse - architecture, schema/data-model, build-vs-buy, a migration direction - and directly invocable when

• executing-work

  Autonomous execution of an approved spec or plan from docs/plans/. Use when I say to proceed, implement, build, or continue an agreed plan, or when resuming a session that has an In Progress plan doc.

• finishing-work

  Completion pass for a finished effort. Use when all sections of a plan in docs/plans/ are implemented, or I say wrap up, finish, close out, or hand off.

• kaizen

  Use when running a kaizen pass on the kit: an explicit kaizen request, accepting an end-of-effort or session-start offer to reflect on captured friction, or applying a pending kaizen brief in the kit repo. Jotting a single friction note does not need this skill; the global capture rule covers that.

• kit-doctor

  Validate and repair this machine's grimoire installation. Use when the kit was just installed or updated on a machine, when a kit capability misbehaves (hooks, memory tooling, doctrine not loading), or when I ask to run the doctor, check the install, or verify kit setup.

• kit-goal

  Arm or clear a tree-scoped completion leash for a plan run or an ordered sequence of them. Use when I type /kit-goal <plan path>... to hold an autonomous run to completion across a session swap, /kit-goal clear to release it, or /kit-goal to see what is armed. The kit-native, deterministic alternati

• liaison

  Use when this session holds the liaison seat, the persona whose charter names this skill, or when several client users share one Discord thread with a persona. Triggers: the liaison charter at launch, a message in a shared client thread, shaping what someone asks into a brief for the architect perso

• memory-system

  Use when working with the kit memory store beyond plain memory files: recalling the store at effort start or a seat takeover, reporting what the store recorded, logging or looking up an action outcome, stamping a memory applied, tagging, running the decay pass or pinning against it, recording a type

• operating-instructions

  My core operating doctrine: how to think, decide, build, verify, communicate, and stay in scope. Consult at the START of ANY non-trivial task (coding, design, debugging, review, or writing) and whenever unsure how I want work approached. This is the always-apply house ruleset, not an optional refere

• peer-sessions

  Use when reading the roster of live sessions, messaging another session, or acting on a message one sent. Triggers: the ListAgents or SendMessage tools, cross-session coordination, a sibling session in this or another repo, coordinating with a session working the same tree, a warm consult of a peer

• prose-register

  Use when writing or reviewing any prose for a reader beyond a single passage: a deliverable document, an article, a ticket, an email and a pull request body are among the instances. Use also for any piece that names a voice.

• responding-to-review

  Use when a review agent returns findings, when I give feedback or a correction, or before implementing a suggestion from either, especially when it seems wrong, unclear, or larger than the problem. Triggers: adversarial/blind/security/qa/docs review output to adjudicate, a 'you're right' about to be

• role

  Use when taking a seat with /role <Seat>, writing or reading a session registry entry, or resolving whether a seat holds the operator's standing delegation or another standing grant. Triggers: /role, a seat takeover or handoff, a file under ~/.claude/coordinator/, scoped direction from a senior seat

• sql-style

  My T-SQL house style. Use whenever writing or modifying ANY SQL: stored procedures, tables, functions, indexes, install or deployment scripts, or ad-hoc queries. Signature traits: shell-then-ALTER deployment, banner-comment headers, leading commas, tab-aligned columns, leading semicolons, audit-logg

• standing-watch

  Use when a session watches a live system it does not own on a repeating loop, waking on a timer or an operator message, checking, intervening, and sleeping again. Triggers: a watch or babysitter session, a loop armed with /loop or a self-authored wake prompt, a runbook to follow each pass, a ledger

• systematic-debugging

  Root-cause debugging discipline. Use whenever investigating a bug, failure, unexpected behavior, failing test, or production incident - BEFORE proposing any fix. Triggers include 'bug', 'broken', 'failing', 'why is this happening', error reports, and especially any situation where a previous fix att

• testing-discipline

  Use when writing a test, deciding whether a change earns one or whether a test already in the tree still earns its keep, choosing which tests to run after a fix, or reading a red or a wall-clock figure. Triggers: a new test or test file, a test whose subject moved or was deleted, a suite audit, a te

• writing-skills

  Use when creating a skill for this kit, editing one, or deciding whether a wording change to a behavior-shaping skill will actually change behavior. Also use when amending curated prose the kit ships: a skill, an agent charter, the output style, a README, a plan doc, or a doc under docs/. Triggers:

Subagents (18)

• adversarial-reviewer

  Fresh-context adversarial code reviewer. Use PROACTIVELY after completing each section of planned work, once over the whole changeset at the end of an effort, or when asked to review changes. Invoke with the spec/plan path and the base git ref (or changed-file list). Reviews for spec compliance firs

• blind-reader

  Use when a deliverable document needs a blind outside-reader review. Dispatched as a named reader persona with the document paths only - never an intent story alongside them, though a spec or plan handed as the document under review is the subject rather than contamination; reading without the inten

• blind-reviewer

  Blind diff-only correctness reviewer, dispatched in parallel with the adversarial-reviewer on each section of planned work. Invoke with the base git ref or changed-file list only - never the spec, the plan, or the section name; reviewing without the intent story is the point. Returns severity-ranked

• consultant

  Fresh-context ruling agent for a stuck orchestrator mid-execution. Use PROACTIVELY on a second failed attempt at the same problem, before a BLOCKED that turns on a decision, at a debugging dead end, or on a weighty decision the spec does not cover. Rules on the question and returns an implementable

• corpus-drafter

  Read-only drafter for the corpus-compression and mechanism-cut plans. Dispatched only through tools/corpus-compression/workflow.mjs with one document path, its rationale-ledger heading and, for the mechanism cut, the document's cut-list rows. Returns the proposed document text and the proposed ledge

• council-member

  Read-only design-stage reviewer dispatched by the design-council skill, one per lens. Takes an evidence-grounded position on competing approaches at an architecture fork, names its strongest objections, and in cross-examination rounds engages opposing objections - conceding, rebutting with evidence,

• design-facilitator

  Neutral convergence judge for the design-council skill. After each round it maps where the lenses agree and genuinely disagree, names the crux of each dispute, classifies convergence as evidence-resolved or capitulation, and decides another round / converged / deadlock. Read-only; owns the convergen

• docs-curator

  Documentation curator and drift detector. Use during finishing-work after QA and reviews pass, or when asked to document a codebase or prepare a handoff. Invoke with the spec/plan path. Reads the as-built code fresh, updates the project's docs/, and returns a Drift Report comparing spec vs. as-built

• implementer-fable

  Scoped implementation agent, top tier - no model pin: it inherits the main session's model, and a below-fable session dispatches it with the explicit fable model override, so the top tier always runs the strongest model available. Use to implement a single Section of Work from an approved spec when

• implementer-haiku

  Scoped implementation agent, Haiku tier. Use to implement a single pure-transcription Section of Work from an approved spec - the brief names an exact sibling to clone with substitutions and a self-surfacing gate (a build or existing test that fails loudly if the output is wrong). Dispatch with a br

• implementer-opus

  Scoped implementation agent, Opus tier. Use to implement a single Section of Work from an approved spec when the section has moderate complexity - multi-file coordination, nuanced refactoring, performance-sensitive logic, or mild ambiguity within a clear design. Dispatch with a brief built from the

• implementer-sonnet

  Scoped implementation agent, Sonnet tier. Use to implement a single well-defined Section of Work from an approved spec when the section is mechanical or well-bounded - clear contract, an existing sibling pattern to mimic, low integration risk. Dispatch with a brief built from the executing-work skil

• performance-reviewer

  Advisory performance review agent for any production codebase. Use PROACTIVELY when a work section's delta spawns a process, runs on a per-tool-call path, walks the tree, holds a lock, waits on another process, or queries a store, which is the trigger the executing-work skill's review step names for

• plan-reviewer

  Fresh-context adversarial reviewer of a spec against its own Goal, before the plan is armed. Dispatched by the brainstorming skill after the author's self-review and the blind read, with the spec path alone and never the design conversation. Reads the Goal and Intent first, then each section against

• prose-reviewer

  Fresh-context adversarial prose reviewer. Use PROACTIVELY after completing a section whose deliverable is a document for a named audience, once over every document in scope at the end of a documents effort, or when asked to review a deliverable document. Invoke with the spec path, the document paths

• qa-verifier

  Behavioral verification agent. Use at the end of an effort (finishing-work) or when asked to verify that implemented work actually functions. Invoke with the spec/plan path. Runs the build, runs the tests, and checks every acceptance criterion in the spec with evidence. Reports pass/fail; never fixe

• scope-adjudicator

  Fresh-context judge of whether a review finding, or a mechanism a fix proposes to add, serves the plan's Goal. Dispatched with the plan's what and never its how, on a fixed brief that carries no lean, no prior consult and no fix narrative. It rules one finding into one of three buckets (refuse, acce

• security-reviewer

  Advisory security review agent for any production codebase, with deep specialization in C#/.NET and SQL Server (procedure-only data access, SOC 2 audits). Use PROACTIVELY when a work section touches a surface the executing-work skill's review step names as this reviewer's trigger, and always over th

Hooks (15)

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.js"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/branch-reaper-nudge.js"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/kit-version-nudge.js"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/doctrine-refresh.js"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/hook-canary.js"

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/memory-session.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/hook-dispatch.js" PreToolUse

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/hook-dispatch.js" PostToolUse

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/hooks/memory-recognition-nudge.js"

• SubagentStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/memory-recognition-nudge.js"

• SessionEnd

  node "${CLAUDE_PLUGIN_ROOT}/hooks/jev-session-end.js"

• PreCompact

  node "${CLAUDE_PLUGIN_ROOT}/hooks/kit-compact-gate.js"

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/stop-docs-hygiene.js"

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/kit-goal-stop.js"

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/seat-stop.js"