~ / rigs / aishwaryajayanth1820-git / code_graph_agentic_observable_coding

aishwaryajayanth1820-git/code_graph_agentic_observable_coding

Make AI coding agents observable and governed: a C4 code graph that records contracts, tasks, ADRs and EVAL verdicts, blocks unapproved changes, and shows every change in a live web UI. Includes Claude Code agents, skills and playbooks; wor

↗ GitHub ★ 1 Apache-2.0 updated 1mo ago project Claude CodeCodex
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.4k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit aishwaryajayanth1820-git/code_graph_agentic_observable_coding/.claude ./rig-code_graph_agentic_observable_coding  # inspect, then merge into .claude/

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit aishwaryajayanth1820-git/code_graph_agentic_observable_coding/.claude/skills/c4-design .claude/skills/c4-design
$ npx degit aishwaryajayanth1820-git/code_graph_agentic_observable_coding/.claude/skills/code-graph .claude/skills/code-graph
$ npx degit aishwaryajayanth1820-git/code_graph_agentic_observable_coding/.claude/skills/orchestrate-cycle .claude/skills/orchestrate-cycle
$ curl -fsSL --create-dirs -o .claude/agents/app-design-reviewer.md https://raw.githubusercontent.com/aishwaryajayanth1820-git/code_graph_agentic_observable_coding/main/.claude/agents/app-design-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/arch-reviewer.md https://raw.githubusercontent.com/aishwaryajayanth1820-git/code_graph_agentic_observable_coding/main/.claude/agents/arch-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/aishwaryajayanth1820-git/code_graph_agentic_observable_coding/main/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/aishwaryajayanth1820-git/code_graph_agentic_observable_coding/main/.claude/agents/coder.md
$ curl -fsSL --create-dirs -o .claude/agents/performance-reviewer.md https://raw.githubusercontent.com/aishwaryajayanth1820-git/code_graph_agentic_observable_coding/main/.claude/agents/performance-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/aishwaryajayanth1820-git/code_graph_agentic_observable_coding/main/.claude/agents/security-reviewer.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

Skills (3)

Subagents (6)

app-design-reviewerApplication design reviewer. Checks completed code-graph tasks against the APP_DESIGN EVALs - SOLID, whether declared extension points really work, interface contract clarity, dependency injection, co
arch-reviewerArchitecture reviewer. Checks completed code-graph tasks against the ARCH EVALs - dependency direction, component boundaries, declared dependencies, cycles, coupling, graph-to-code consistency, platfo
code-reviewerCode and business-logic reviewer. Checks completed code-graph tasks against the CODE and BUSINESS EVALs - acceptance criteria and business invariants, unit test coverage of contract functions, error h
coderImplements one code-graph task (a set of C4 nodes) with unit tests, against the contracts recorded in the graph, following platform-first SOLID design, and records progress in the code graph. Use for
performance-reviewerPerformance reviewer. Checks completed code-graph tasks against the PERFORMANCE EVALs - per-event hot-path cost, I/O and N+1 on hot paths, bounded memory, caching and batching, behaviour under varying
security-reviewerSecurity reviewer. Checks completed code-graph tasks against the SECURITY EVALs - input validation at trust boundaries, secrets and PII handling, injection and unsafe deserialisation, authorisation on

Similar rigs

copied ✓