72 tagged adr, measured the same way as everything else here.
Browse within: architecture 23architecture-decision-records 15claude-plugin 14backstage 11developer-experience 11annotations 9architectural-decision-records 9code-documentation 9architecture-review 8ci 6prd 6product-management 6agentic-engineering 5agentic-workflows 5
Agent Claude Code
Use when a diff, planned change, or OpenSpec proposal touches the checker kernel — packages/claims/src/checkClaims.ts, witness.ts, wiring.ts, rules.ts, or config.ts — and you need a review of whether the change respects the kernel's own semantics: which verdict union a new verdict belongs to, whether its pass/fail…
Agent Claude Code
Use as the FINAL stage of a proposal-to-pr run to record what happened, as one retrospective file under .claude/retrospectives/. Dispatched fresh, having NOT done the work, so it reads artefacts — the pipeline state file, review-evidence.md and its ## Probe — stage 2 score, progress.md, git history — rather than the…
Agent Claude Code
You are the ADR Guard, responsible for ensuring code changes comply with applicable Architecture Decision Records.
Agent Claude Code
You are the ADR Steward, responsible for managing Architecture Decision Records in this repository.
Agent Claude Code
Cost-aware dispatcher for skilldrop skills (Claude Code implementation of the provider-neutral routing spec in model-routing.json). Given a skill name + the task input, looks up the skill's abstract tier, applies cheap no-LLM heuristics (input size, ambiguity, user override), resolves the tier to a concrete model via…
Agent
Adversarial reviewer of just-written code and tests. Hunts for what will break — edge cases the first pass missed, assumptions that won't survive future requirements, what a staff engineer would push back on in review, and test-coverage gaps. Delegate to it right after a feature is declared "done", before opening a PR…
Agent
Security reviewer of just-written code and its dependencies. Hunts for exploitable weaknesses in the change — missing authz, injection, secret exposure, SSRF, unsafe deserialization, path traversal, weak crypto, and risky new dependencies. Does NOT hunt general bugs (that's devils-advocate) or model a design's threat…
Agent
Independent critique of a design (PRD + TDD set + accepted ADRs) BEFORE the design PR is opened. Checks requirement traceability, interface specification, the required alternatives analysis, ADR conflicts, and scope coherence. Use at /tdd-author close-out.
Agent
Reviews code for security vulnerabilities. Use after implementing auth, input handling, data access, or anything that touches secrets or untrusted input.
Agent
Codex can install the complete koment plugin or use generated project files. Both forms require a released koment binary on PATH.
Agent
Hermes Agent is Nous Research's self-hosted agent. It reads MCP servers from mcpservers in its config.yaml, typically at /.hermes/config.yaml.
Agent
Agent "other" from koment-dev/koment, covering any other mcp client, stdio — the default, http — when the agent isn't on the same machine, the tools and check it works without a client.