Skill Claude CodeCodex
Implement an already-approved plan from swarm-report/ -plan.md. Routes each task to the executing agent that owns its file scope (frontend / backend / devops / mobile), runs the tests, writes an implementation report. Use AFTER /code-plan, never before.
Skill Claude CodeCodex
Find the root cause of a bug or failing test. Spawns 1 debugger subagent that reproduces, ladders hypotheses, isolates with evidence, and applies the minimal fix. Use when a test fails, /code-build reports blocked, or "X stopped working". Does NOT design features (that's /code-plan).
Skill Claude CodeCodex
Design a feature before writing code. Spawns planner + skeptic subagents that read the Memory Bank, argue, and write a plan to swarm-report/. Use BEFORE /code-build, for any feature touching 2+ files or with unclear scope. Skip for typos and one-line fixes.
Skill Claude CodeCodex
Review a finished change against its plan. Spawns 1 reviewer subagent, reports ship/rework with severity-tagged findings. Use AFTER /code-build.
Agent Claude Code
Orchestrates the content pipeline from idea to publication: choosing the format (post / article / tutorial) → drafting via the corresponding skill → edits → publication. Invokes content-tg-post, content-article-draft, content-tutorial-structure. Use when "shape this thought," "I have an idea — what do I do with it,"…
Skill Claude CodeCodex
Turns an idea, a series of notes, or raw material into an article draft (Habr / Medium / personal blog) — with a TL;DR, a thesis → arguments → example → implication structure, and an authorial voice. Use when "write an article," "shape these thoughts into a long-read," "make a Habr post," "article draft.".
Skill Claude CodeCodex
Structures a technical tutorial — prerequisites, a "after reading this you'll be able to do X" goal, numbered steps with commands and checks, troubleshooting, cleanup. Doesn't write the full text: it produces a correct skeleton for the author to fill in with details. Use when "write a tutorial," "put together…
Skill Claude Code
A content factory — turns a single source into a full content package in one pass. Takes as input a finished article, a video transcript, OR (if there's only a topic) offers to run deep research and assemble a source itself. Output: a 1500–2500 word article, 10 threads, 5 Reels/Shorts scripts, 5 posts…
Skill Claude CodeCodex needs its repo
A skill for humanizing Russian-language text. Removes signs of AI generation, makes the text feel alive. ALWAYS use this when the user asks to: humanize a text, remove traces of a neural network, make a text lively/natural, rewrite it like a human, humanize in Russian, remove officialese, remove wateriness/filler…
Skill Claude CodeCodex
Turns an idea, a note, or raw text into a ready-to-post Telegram channel post — tight, thesis-first, in the author's voice, within 500-1500 characters. Use when the user wants "write a TG post," "shape this thought for the channel," "short post," "tg post," "shape an idea for subscribers.".
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
Skill Claude Code
Defragment and re-actualize a project memory bank (the .assistant/ knowledge base + the project's auto-memory). Reads everything that changed in the repo since the last defrag, finds where the memory bank has gone stale or accumulated amendment-on-amendment "patches", folds the patches into clean current-state docs…
Skill Claude Code
Maintains a lightweight, always-current "project encyclopedia" in .memory-bank/ — capturing architecture, stack, conventions, key entities, and active tasks. After each meaningful change, the AI suggests concise updates or explicitly confirms no update is needed.
Skill Claude CodeCodex
Domain Driven Harness for Claude Code.
Agent Claude Code
Consilium role. Reviews infrastructure architecture: platform design, service topology, K8s workload design, inter-service dependencies, IaC structure, scalability, tech debt. Does NOT write code or configs.
Agent Claude Code
Executing agent. Writes GitLab CI/CD pipelines, shared templates, Dockerfile optimizations. Scope: /.gitlab-ci.yml, ci-templates/, abp/ci-templates/. Corporate registry and Nexus only.
Agent Claude Code
Consilium role. Root cause analysis for infrastructure incidents: pod crashes, OOMKills, network issues, ArgoCD sync failures, pipeline failures, performance degradation, Redis/DB issues. Does NOT write code.
Agent Claude Code
Executing agent. Writes and maintains Helm charts: Chart.yaml, templates/, values.yaml, helpers. Scope: davinci/kubernetes/apps/helm/, /Chart.yaml, /values.yaml.
Agent Claude Code
Executing agent. Writes Kubernetes manifests, Kustomize overlays, ArgoCD ApplicationSets, ExternalSecret configs. Scope: k8s/, davinci/ (excluding helm/ subdirs). GitOps — prod deploy only via ArgoCD.
Agent Claude Code
Consilium role. Reviews infrastructure security: K8s RBAC, network policies, secrets management (Vault/ESO), container security, supply chain, CIS benchmarks, OWASP for APIs. Does NOT write code.
Agent Claude Code
Consilium role. Reviews SRE practices: SLO/SLA/error budgets, observability (metrics/logs/traces), alerting rules, runbooks, incident response, capacity planning, post-mortems. Does NOT write code.
Agent Claude Code
Orchestrates the full cycle of a git change: create a branch → atomic commits following Conventional Commits → PR description → merge → semver tag (if it's a release). Calls the skills git-conventional-commit, git-pr-description, git-release-tag. Use when the task is to carry a change through git from branch to…
Skill Claude CodeCodex
Builds a Conventional Commits commit message for the current changes in git. Analyzes the staged diff (or unstaged, if staged is empty), determines type/scope, writes the subject and, if needed, a body. Use when the user wants to "make a commit", "commit the changes", "commit this", "write a commit message", "commit…
Skill Claude CodeCodex
Builds a Pull Request description from the diff of the current branch against the base branch (main/master). Analyzes all commits, extracts "why / what / how to verify", captures breaking changes. Use when the user wants to "describe the PR", "write a description for the pull request", "put together a PR", "push and…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: