~ / rigs / bogheorghiu / ex-cog-dev

bogheorghiu/ex-cog-dev

ex-cog — externalized cognition. Four Claude Code plugins. research-toolkit — self-checking investigation & verification. makers-toolkit — build-discipline & prompt-design. vasana-system — cross-session pattern memory (forms, not just facts

↗ GitHub ★ 2 MIT updated 24d ago project Claude Code Claude plugin
field: unknown workflow: ResearchTesting & TDDPR / code reviewDebuggingDocs runs claude in CI
stack: Python
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~15.7k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 18/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ claude mcp add financial-mcp -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=research-toolkit/mcp-servers/financial-mcp' financial-mcp
$ claude mcp add transparency-mcp -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=research-toolkit/mcp-servers/transparency-mcp' transparency-mcp
$ claude mcp add relational-memory -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=vasana-system/mcp-servers/relational-memory' relational-memory
$ claude mcp add edge-graph -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=vasana-system/mcp-servers/edge-graph' edge-graph
$ npx degit bogheorghiu/ex-cog-dev/.claude ./rig-ex-cog-dev  # 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.

$ claude mcp add financial-mcp -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=research-toolkit/mcp-servers/financial-mcp' financial-mcp
$ claude mcp add transparency-mcp -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=research-toolkit/mcp-servers/transparency-mcp' transparency-mcp
$ claude mcp add relational-memory -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=vasana-system/mcp-servers/relational-memory' relational-memory
$ claude mcp add edge-graph -- uvx --from 'git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory=vasana-system/mcp-servers/edge-graph' edge-graph
$ npx degit bogheorghiu/ex-cog-dev/makers-toolkit/skills/intrinsic-prompt-design .claude/skills/intrinsic-prompt-design
$ npx degit bogheorghiu/ex-cog-dev/makers-toolkit/skills/skill-activation-testing .claude/skills/skill-activation-testing
$ npx degit bogheorghiu/ex-cog-dev/makers-toolkit/skills/system-pilot .claude/skills/system-pilot
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/cui-bono .claude/skills/cui-bono
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/deep-investigation-protocol .claude/skills/deep-investigation-protocol
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/dev-job-defense-ties .claude/skills/dev-job-defense-ties
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/dialectic-spiral .claude/skills/dialectic-spiral
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/engage-the-disfavored .claude/skills/engage-the-disfavored
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/frame-rotation .claude/skills/frame-rotation
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/ground-level-triangulation .claude/skills/ground-level-triangulation
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/iterative-verification .claude/skills/iterative-verification
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/kernel-shell .claude/skills/kernel-shell
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/label-function-analysis .claude/skills/label-function-analysis
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/macro-monitor .claude/skills/macro-monitor
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/manufactured-confusion-detection .claude/skills/manufactured-confusion-detection
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/manufactured-consensus-detection .claude/skills/manufactured-consensus-detection
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/research .claude/skills/research
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/saturation-sweep .claude/skills/saturation-sweep
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/source-dossier .claude/skills/source-dossier
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/source-omission-analysis .claude/skills/source-omission-analysis
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/standpoint-pass .claude/skills/standpoint-pass
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/substack-research .claude/skills/substack-research
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/text-deconstruction .claude/skills/text-deconstruction
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/video-transcript-extraction .claude/skills/video-transcript-extraction
$ npx degit bogheorghiu/ex-cog-dev/research-toolkit/skills/youtube-research .claude/skills/youtube-research
$ npx degit bogheorghiu/ex-cog-dev/security-toolkit/skills/pii-gate .claude/skills/pii-gate
$ npx degit bogheorghiu/ex-cog-dev/security-toolkit/skills/pr-merge-guard .claude/skills/pr-merge-guard
$ npx degit bogheorghiu/ex-cog-dev/security-toolkit/skills/windows-wsl-security-verification .claude/skills/windows-wsl-security-verification
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/break-pattern .claude/skills/break-pattern
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/check-assumptions .claude/skills/check-assumptions
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/find-similar .claude/skills/find-similar
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/iterative-loop-engine .claude/skills/iterative-loop-engine
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/pattern-library .claude/skills/pattern-library
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/record-pattern .claude/skills/record-pattern
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/self-improving-investigation .claude/skills/self-improving-investigation
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/temporal-shaping .claude/skills/temporal-shaping
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/test-pattern .claude/skills/test-pattern
$ npx degit bogheorghiu/ex-cog-dev/vasana-system/skills/vasana .claude/skills/vasana
$ curl -fsSL --create-dirs -o .claude/agents/review-triage.md https://raw.githubusercontent.com/bogheorghiu/ex-cog-dev/main/.claude/agents/review-triage.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 *)"
    ]
  }
}

MCP servers (4)

serversourceest. tokens
git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory · "financial-mcp" pypi 2.5k
git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory · "transparency-mcp" pypi 2.5k
git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory · "relational-memory" pypi 2.5k
git+https://github.com/bogheorghiu/ex-cog-dev#subdirectory · "edge-graph" pypi 2.5k

Skills (38)

Subagents (1)

review-triage
model: opus
Classify prose-review comments on a pull request as real, false positive, or rule gap. Invoked by /review-triage; analysis only, never posts or edits.

Slash commands (1)

/review-triage

Plugins (2)

security-toolkit@ex-cog-devmakers-toolkit@ex-cog-dev

Similar rigs

copied ✓