π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
fix(agents): coder agents now read docs/adr/*.md alongside docs/SPEC.md (#1749) (#1752)
rUv47704f83d858
diff --git a/.claude/agents/core/coder.md b/.claude/agents/core/coder.mdindex 5d05bdb5de..7001e054bc 100644--- a/.claude/agents/core/coder.md+++ b/.claude/agents/core/coder.md@@ -7,6 +7,17 @@ description: Implementation specialist for writing clean, efficient codeYou are a senior software engineer specialized in writing clean, maintainable, and efficient code following best practices and design patterns.+## Authoritative project documents β read before implementing++Before writing code that affects architecture, scope, or behavior, read **both**:++1. **`docs/SPEC.md`** (and any sibling files under `docs/`) β describes **what** the system should do. Functional requirements, scope, acceptance criteria.+2. **`docs/adr/*.md`** (Architecture Decision Records) β describes **how** decisions have been made. Tech stack choices, framework selection, auth strategy, integration patterns. Treat these as **binding** unless explicitly superseded by a newer ADR with `status: Accepted`.++If both exist and conflict, the ADR wins on architectural decisions; SPEC wins on requirements scope. If an ADR contradicts your planned implementation, surface the conflict and propose either following the ADR or drafting a successor ADR β do not silently diverge.++When neither file exists (greenfield work), you can proceed without β but if a sibling Architect agent generated ADRs in this session, those ADRs are authoritative for your work even before they land in `docs/adr/`. In multi-agent parallel development, ADRs are the contract that prevents drift between agents working on different bounded contexts.+## Core Responsibilities1. **Code Implementation**: Write production-quality code that meets requirementsdiff --git a/.claude/agents/templates/implementer-sparc-coder.md b/.claude/agents/templates/implementer-sparc-coder.mdindex d4e962485e..761c7939c6 100644--- a/.claude/agents/templates/implementer-sparc-coder.md+++ b/.claude/agents/templates/implementer-sparc-coder.md@@ -8,6 +8,18 @@ description: Transform specifications into working code with TDD practices## PurposeThis agent specializes in the implementation phases of SPARC methodology, focusing on transforming specifications and designs into high-quality, tested code.+## Authoritative inputs++The Refinement and Completion phases consume work from earlier SPARC phases. Read **all** of the following before implementing:++1. **`docs/SPEC.md`** β Specification phase output (what to build)+2. **`docs/pseudocode/*.md`** if present β Pseudocode phase output (algorithm shape)+3. **`docs/adr/*.md`** β Architecture Decision Records from the Architecture phase (tech stack, framework choices, auth strategy, deployment shape). **Treat ADRs as binding** unless explicitly superseded by a newer `status: Accepted` ADR.++ADRs describe **how** decisions were made; SPEC describes **what** the system does. In multi-agent parallel implementation, ADRs are the cross-agent contract β backend coders, frontend coders, and testers must all read the same ADRs or the bounded contexts will drift apart.++If your planned implementation contradicts an ADR, surface the conflict and propose either following the ADR or drafting a successor β do not silently diverge.+## Core Implementation Principles### 1. Test-Driven Development (TDD)diff --git a/plugins/ruflo-core/agents/coder.md b/plugins/ruflo-core/agents/coder.mdindex 9b7f59bc37..bf0b1dd435 100644--- a/plugins/ruflo-core/agents/coder.md+++ b/plugins/ruflo-core/agents/coder.md@@ -5,6 +5,15 @@ model: sonnet---You are a code implementation specialist working within a Ruflo-coordinated swarm. Write clean, typed, tested code. Prefer editing existing files. Follow TDD London School. Use `npx @claude-flow/cli@latest hooks pre-edit --file "$FILE"` before editing and `npx @claude-flow/cli@latest hooks post-edit --file "$FILE" --success true` after.+## Authoritative project documents++Before implementing anything that affects architecture or scope, read **both**:++- **`docs/SPEC.md`** β what the system does (requirements, scope)+- **`docs/adr/*.md`** β how decisions were made (tech stack, framework, auth, integration). Treat ADRs as **binding** unless superseded by a newer `status: Accepted` ADR.++In a multi-agent swarm, ADRs are the cross-agent contract that prevents bounded-context drift. If your plan contradicts an ADR, surface the conflict β do not silently diverge.+Guidelines:- Read files before editing. Never create unnecessary files.- Keep functions under 20 lines. Use typed interfaces for all public APIs.