~ / rigs / rajasdevel / outcomebound

rajasdevel/outcomebound

Toward trustworthy delegation to coding agents

↗ GitHub ★ 0 Apache-2.0 updated 16d ago project Claude CodeCodex
stack: Python
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~6.4k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 8/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit rajasdevel/outcomebound/.claude ./rig-outcomebound  # 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 rajasdevel/outcomebound/.agents/skills/decision-brief .claude/skills/decision-brief
$ npx degit rajasdevel/outcomebound/.agents/skills/diagnose .claude/skills/diagnose
$ npx degit rajasdevel/outcomebound/.agents/skills/explain-spec .claude/skills/explain-spec
$ npx degit rajasdevel/outcomebound/.agents/skills/explorable .claude/skills/explorable
$ npx degit rajasdevel/outcomebound/.agents/skills/gather-requirements .claude/skills/gather-requirements
$ npx degit rajasdevel/outcomebound/.agents/skills/hand-off-tickets .claude/skills/hand-off-tickets
$ npx degit rajasdevel/outcomebound/.agents/skills/land-change .claude/skills/land-change
$ npx degit rajasdevel/outcomebound/.agents/skills/review-council .claude/skills/review-council
$ npx degit rajasdevel/outcomebound/.agents/skills/review-findings .claude/skills/review-findings
$ npx degit rajasdevel/outcomebound/.agents/skills/run-acceptance .claude/skills/run-acceptance
$ npx degit rajasdevel/outcomebound/.agents/skills/slice-tickets .claude/skills/slice-tickets
$ npx degit rajasdevel/outcomebound/.agents/skills/sync-tracker .claude/skills/sync-tracker
$ npx degit rajasdevel/outcomebound/.agents/skills/tests-worth-keeping .claude/skills/tests-worth-keeping
$ npx degit rajasdevel/outcomebound/.agents/skills/using-outcomebound .claude/skills/using-outcomebound
$ npx degit rajasdevel/outcomebound/skills/adopt-outcomebound .claude/skills/adopt-outcomebound

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 (15)

Similar rigs

copied ✓