Instructions file CodexOpenCode
Instructions for alexeyshishin/as-skill, covering agents.md, what this repository is, always-on skill, architecture and current domains.
4 12d ago C 3,578 tokens
original MIT
Agent
You find the root cause of a bug or failing test. You diagnose first; you fix only the one thing the evidence points to.
4 12d ago A 0 tokens
original MIT
code-planner
03Agent
You design an implementation plan for one feature. You do NOT write code.
4 12d ago A 0 tokens
original MIT
Agent
You review a finished change against its plan. Read-only. You do NOT fix.
4 12d ago A 0 tokens
original MIT
code-skeptic
05Agent
You attack a proposed feature and its plan. Find what breaks it. You do NOT write code and you do NOT soften findings.
4 12d ago A 0 tokens
original MIT
code-build
06Skill 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.
4 12d ago A 57 tokens
original MIT
code-debug
07Skill 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).
4 12d ago A 67 tokens
original MIT
code-plan
08Skill 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.
4 12d ago A 61 tokens
original MIT
code-review
09Skill Claude CodeCodex
Review a finished change against its plan. Spawns 1 reviewer subagent, reports ship/rework with severity-tagged findings. Use AFTER /code-build.
4 12d ago A 35 tokens
original MIT
Agent
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,"…
4 12d ago A 96 tokens
original MIT
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.".
4 12d ago A 81 tokens
original MIT
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…
4 12d ago A 90 tokens
original MIT
Skill Claude CodeCodex
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…
4 12d ago A 172 tokens
original MIT
Skill Claude CodeCodex
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…
4 12d ago A 147 tokens
original MIT
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.".
4 12d ago A 76 tokens
original MIT
caveman
16Skill 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"…
4 12d ago A 102 tokens
copy · 72% MIT
Skill Claude CodeCodex
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…
4 12d ago A 143 tokens
original MIT
memory-bank
18Skill Claude CodeCodex
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.
4 12d ago A 53 tokens
original MIT
swarm-report
19Skill Claude CodeCodex
Domain Driven Harness for Claude Code.
4 12d ago not scanned
tokens not measured
original MIT
architect
20Agent
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.
4 12d ago A 42 tokens
original MIT
ci-agent
21Agent
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.
4 12d ago A 49 tokens
original MIT
diagnostics
22Agent
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.
4 12d ago A 46 tokens
original MIT
helm-agent
23Agent
Executing agent. Writes and maintains Helm charts: Chart.yaml, templates/, values.yaml, helpers. Scope: davinci/kubernetes/apps/helm/, /Chart.yaml, /values.yaml.
4 12d ago A 44 tokens
original MIT
k8s-agent
24Agent
Executing agent. Writes Kubernetes manifests, Kustomize overlays, ArgoCD ApplicationSets, ExternalSecret configs. Scope: k8s/, davinci/ (excluding helm/ subdirs). GitOps — prod deploy only via ArgoCD.
4 12d ago A 55 tokens
original MIT