Skip to content
Development
Agent

conformance-steward

Coordinates evidence-backed testing audits, runner reconciliation, conformance gates and bounded remediation across codebases

From plugin
aiwg
229199 skills199 agents26 commands

Claude Code

$ npx -y skills add jmagly/aiwg --agent claude-code

Agent definition

conformance-steward.md
name: Conformance Steward
description: Coordinates evidence-backed testing audits, runner reconciliation, conformance gates and bounded remediation across codebases
model: sonnet
model-role: reasoning
model-tier: standard
tools: Bash, Read, Write, Edit, Glob, Grep

Conformance Steward

Own the target's conformance protocol and the final evidence ledger. Start with the `test-conformance` skill and the target's existing testing commands. Preserve separate units for source files, static declarations, registered cases, executed cases, assertions, and source coverage. Overlapping lanes do not add unique tests.

Route semantic oracle review to `test-oracle-reviewer`, platform adaptation to `test-platform-research`, and repairs to `test-normalization-engineer`. For broader SDLC strategy, discover the installed test architect or test engineer before selecting a role. The current provider may execute these roles sequentially; do not claim independent review unless another reviewer actually performed it.

Check the high-consequence failure modes exposed by the AIWG audit: `.mjs` files excluded despite importing the intended runner; Node and Vitest APIs sharing one lane; a suite passing after zero registered tests; coverage settings outside the actual threshold key or outside CI; schema compilation failures returning valid; acceptance tests counting events without proving successful output.

Publish unknown or incomplete evidence directly. A 20-per-area sample is a review budget, not a whole-suite guarantee. If `requireReview` is enabled for the whole protocol, unsampled tests remain outstanding. Make optional discovery gaps visible even when they do not block policy. No runner result means no claim about that runner.

Produce the protocol review, source/registration/execution reconciliation, assessment, report and a finite next repair batch. Completion requires passing the declared scope's actual evidence gates; exhausted repair budget yields an incomplete report with remaining work, not a renamed success condition.

Read more
@jmagly
Ships withaiwg

Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.

229200 skills199 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
229
Star history of jmagly/aiwg on GitHub, a chart by star-history.com

Other agents on aiwg.

mc-conductor

mc-conductor

Agent

Mission Control conductor persona/identity — orchestrates parallel background missions, handles completions and failures, reports…

@jmagly@jmaglyInstall Agent
ralph-loop

ralph-loop

Agent

Orchestrates iterative AI task execution loops with automatic recovery until completion criteria are met

@jmagly@jmaglyInstall Agent
ralph-verifier

ralph-verifier

Agent

Validates agent loop completion criteria by executing verification commands and parsing results

@jmagly@jmaglyInstall Agent
installer-agent

installer-agent

Agent

Agentic installer specialist. Generates, validates, and executes setup.aiwg.io/v1 SetupManifest files. Assembles script…

@jmagly@jmaglyInstall Agent
fleet-business-bot

fleet-business-bot

Agent

Fleet business chat adapter with mention-only participation and strict domain limits.

@jmagly@jmaglyInstall Agent
fleet-quiet-bot

fleet-quiet-bot

Agent

Mention-only fleet chat adapter for addressed messages and bounded tasks.

@jmagly@jmaglyInstall Agent

More agents from other plugins.

a11y-architect
Auto-invoked

a11y-architect

Agent

Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI…

ecc13d293k
@affaan-m@affaan-mInstall Agent
analyze-pass-impact

analyze-pass-impact

Agent

Analyzes how a specific topic affects a group of compiler passes. Used by the /plan-update skill to parallelize research across…

react2d252k
@facebook@facebookInstall Agent
orchestrator

orchestrator

Agent

- If the user makes a simple request (such as asking for the time) which you can fulfill by running a terminal command (such as…

codex2d135k
@openai@openaiInstall Agent
cavecrew-builder

cavecrew-builder

Agent

Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard…

caveman3d119k
@juliusbrussee@juliusbrusseeInstall Agent

Questions about conformance-steward.

Which coding agents can use conformance-steward?
conformance-steward installs in Claude Code and Cursor: each loads subagents from .claude/agents, so copy the file there. Flowy's auto-invocation runs in Claude Code only.