mrodgersjs-web/rig-capabilities/adversarial-verification-loop

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

RIG doctrine — Adversarial Verification (non-vacuity) as a code-enforced loop. For every gate you trust: name it → plant a defect and prove the gate goes RED → restore and prove GREEN → keep the planted failure as a regression fixture → seal. A green that won't go red is theater.

Install

npx vskill@latest install mrodgersjs-web/rig-capabilities/adversarial-verification-loop

SKILL.md

Adversarial verification loop

G Guard → R Red (plant, expect FAIL) → N Green (restore, expect PASS) → K Keep fixture → P Proof
   ▲            │ red did not fail          │ green did not pass
   └────────────┴───────────────────────────┘  (max 3 → escalate: the gate is theater)

Step 0

bash
rig-loop activate adversarial-verification-loop --intent "prove <gate> is non-vacuous"

Stages

StageArtifactGateCommand
G Guardguard.md## Gate-under-test, ## What-it-guards, ## Green-command with - cmd:<shell>rig-loop stage G pass
R Redred.mda planted failure recorded whose red command exited ≠0; ## Planted-defect, ## Red-outputrig-loop plant "<defect>" --red "<cmd with defect planted>" --green "<cmd restored>" then rig-loop stage R pass
N Greengreen.mdregistered checks green now; ## Restored, ## Green-outputrig-loop check add "<green cmd>" then rig-loop stage N pass
K Keepfixture.md## Regression-fixture with - file:<test path> or - cmd:<test cmd>rig-loop stage K pass
P Proofproof.jsonsealedrig-loop seal && rig-loop stage P pass

Why the engine, not the prose

rig-loop plant runs both commands itself and records the exit codes. If the "red" command exits 0 the plant is recorded as red_ok: false and stage R stays red — the gate you trusted does not catch the defect. That is the finding; report it, fix the gate, loop.

Honesty notes

  • Plant a real defect in the code or data the gate guards, not a false command.
  • Keep the fixture in the repo's test suite; the K gate only checks you named where.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mrodgersjs-web/rig-capabilities/adversarial-verification-loop/badge)](https://verified-skill.com/skills/mrodgersjs-web/rig-capabilities/adversarial-verification-loop)

Something wrong with this skill or its page? Tell us.