axiom-forge

Plugin axiom-forge from marketplace axiom-forge in xinhi6716/axiom-atropos. Commands read from the repo's manifest — 3 days ago.

Skills (69)

• reproduce-and-fix-issues

  Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.

• setup-benny

  Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker, repository, routing, control, model, or budget settings.

• triage-issue-reports

  Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.

• architect

  Sketch types, signatures, and module structure before code, then stay

• arena

  Spawn N parallel candidates at the same task, pick a base, graft the

• automate-me

  Use for "automate me", "create/update/refresh my -mode skill", "turn/capture

• benchmark-checklist

  Vet a perf measurement (limiter, tuning, limits, errors, repeatability,

• blast-radius

  Find what a change could break somewhere else before it ships, beyond

• bro

  Restate the last message in plain human language, with no jargon.

• codex-research

  Conduct question-driven literature research to explore a field, refine

• correct

  Find the mistakes agents keep repeating in this repo and make each one

• create-formal-verification-skill

  Generate a project-local skill that formally verifies the code where

• create-verification-skill

  Generate a project-local verification skill that drives your app the

• figure-it-out

  Design an auditable playbook when no narrower one fits: a large migration,

• god-mode

  Grant a wish on the current project. The axiom-forge dispatcher sends Codex workers to do the work, and Gemini rewrites their reports in plain language. Needs Claude Code with the axiom-bridge MCP server. Invoke as /god-mode <wish>.

• how

  Use for "how does X work", code walkthroughs before changing something,

• hypothesis-generation

  Formulates evidence-bounded scientific questions, candidate hypotheses,

• in-your-own-words

  Restate in your own words what you think the user's goals are and what

• interrogate

  Use for "interrogate", "adversarial review", "multi-model review", "challenge

• ketchup-video

  Catch the user up like /ketchup, with a short silent video of slides

• ketchup

  Catch the user up on what changed in this chat since their last message,

• literature-review

  Conducts systematic, scoping, and narrative literature reviews using

• maintain-formal-verification-skill

  Bring a project''s formal verification back in line with the code after

• maintain-verification-skill

  Periodic pass that keeps a project''s verification skill and feature

• make-bot-ui

  Use when building a custom UI (page, dashboard, buttons) that should

• no-comments

  Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed

• poteto-help

  Guides users through pstack setup, /poteto-mode, and picking the skill,

• poteto-mode

  poteto's agent style for concise, detailed responses, deliberate subagents,

• principle-attack-the-premise

  Apply when two or more fixes that share one premise have failed the same

• principle-boundary-discipline

  Apply when wiring validation, error handling, or framework adapters.

• principle-build-the-lever

  Apply to any non-trivial work, not just bulk work: edits, migrations,

• principle-encode-lessons-in-structure

  Apply when you catch yourself writing the same instruction a second time,

• principle-exhaust-the-design-space

  Apply when facing a novel UI interaction or architectural decision with

• principle-experience-first

  Apply when product, UX, or feature-scope tradeoffs come up. Choose user

• principle-explain-the-number

  Apply before you trust, report, or act on a number you measured: a speedup,

• principle-fix-root-causes

  Apply when debugging. Trace each symptom back to the first place the

• principle-foundational-thinking

  Apply before writing logic: choosing core types and data structures,

• principle-guard-the-context-window

  Apply when context is filling up: large outputs, long files, repeated

• principle-laziness-protocol

  Apply when refactoring, evaluating diff size, or tempted to add abstractions,

• principle-make-operations-idempotent

  Apply when designing commands, lifecycle steps, or processing loops that

• principle-migrate-callers-then-delete-legacy-apis

  Apply when introducing a new internal API while old callers still exist.

• principle-minimize-reader-load

  Apply when reviewing or shaping code that's hard to trace. Count layers

• principle-model-the-domain

  Apply when writing stateful logic, or when code branches a lot or repeats

• principle-never-block-on-the-human

  Apply when tempted to ask 'should I do X?' on reversible work.

• principle-outcome-oriented-execution

  Apply during planned rewrites and migrations with explicit phase boundaries.

• principle-prove-it-works

  Apply after completing a task, before declaring done. Verify against

• principle-redesign-from-first-principles

  Apply when integrating a new requirement into an existing design.

• principle-separate-before-serializing-shared-state

  Apply when concurrent actors might write to the same file, branch, key,

• principle-sequence-verifiable-units

  Apply to multi-step work (sweeps, migrations, runs of similar edits)

• principle-subtract-before-you-add

  Apply when sequencing an addition, refactor, or rewrite. Remove dead

• principle-test-behavior-not-implementation

  Apply when you write, change, or keep a test. Assert what the code's

• principle-type-system-discipline

  Apply when designing types, reviewing a function signature, or writing

• recall

  Reconstruct your recent working context from your own chat history, live

• reflect

  Spawn three parallel review subagents over the active transcript, surface

• research-suite

  Coordinate scientific literature research, hypothesis design, statistics, evidence critique and iterative research with the bundled scientific skills and Pstack. Use for a scientific project spanning these activities or an explicit research-suite request; select only the workflows needed.

• rsi-anything

  Use RSI-Anything as a reasoning framework for iterative scientific research: propose alternatives, state predictions, compare external feedback, and retain supported improvements. Use for multi-round research or explicit RSI requests. No model deployment by default.

• scientific-critical-thinking

  Evaluates scientific claims and evidence quality. Applies to experimental

• setup-pstack

  Configure which models pstack uses per role and at what reasoning budget.

• sharpen

  Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.

• show-me-your-work

  Keep a reviewable decision trail for long-running or unattended work:

• statechart

  Draw how any system moves between states, such as a product flow, a protocol,

• statistical-analysis

  Guided statistical analysis for research data - test selection, assumption

• swarm

  Fan out N parallel workers, drain them, and return one report. Use for

• tdd

  Use only when the user explicitly asks for TDD, a failing test, or a

• teach

  Explain a body of work plainly so a person actually understands it. Runs

• technical-writing

  Layered technical-writing standard: Diátaxis structure, Google developer

• typescript-best-practices

  TypeScript best practices. Use when reading or editing any .ts or .tsx

• unslop

  Cut AI tells from any writing.

• why

  Use for 'why does X work this way', 'why we picked Y', design rationale,

Subagents (2)

• dispatcher

  Carries out a wish on a codebase by splitting it into Codex worker units, dispatching each through the axiom bridge, verifying the results and reporting back. Give it the wish and the project's absolute directory.

• memory-keeper

  After a wish is done, distills its verified units into long-run memory for later briefs and adds one line to the project's history. Give it the orch store path, the program slug, the project's absolute directory and the wish.

MCP servers (1)

• axiom-bridge

  runs: ${CLAUDE_PLUGIN_ROOT}/bin/atropos bridge

Similar plugins