agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/audit-validator-independence/SKILL.md

audit-validator-independence

Skill504 starsChanged 49 days agoApache-2.0View on GitHub

Audit whether a validator, benchmark, sandbox, or test can pass by construction because it embeds the same assumptions as the theory it claims to validate. Build a claim×validator-assumption matrix and demand at least one non-circular failure channel.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not perform called SOP operations inline.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

audit-validator-independence

Purpose

Detect validators that pass by construction because they copy the target theory's assumptions.

Input contract

mode_contracts:
  validator: &validator_audit_input
    required: [target_claim, validator, validator_artifacts]
    optional: [data_generation, metric, oracle, acceptance_rule]
    constraints: [validator_assumptions_and_target_assumptions_must_be_separately_listed]
  benchmark: *validator_audit_input
  sandbox: *validator_audit_input
  simulation: *validator_audit_input

Execution protocol

Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.

  1. You MUST load skill enumerate-validator-assumptions to enumerate embedded validator assumptions.
  2. You MUST load skill build-noncircularity-matrix to cross-tabulate target and validator assumptions.
  3. You MUST load skill detect-pass-by-construction to detect copied assumptions. You MUST load skill design-falsification-test to design an independent failure channel. Deviation: if no non-circular channel is feasible, return blocked validation rather than a pass.

Output contract

mode_contracts:
  validator: &validator_audit_output
    produces: [noncircularity_matrix, red_cell_actions, validator_verdict, adversarial_ground_truth_set]
    delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
  benchmark: *validator_audit_output
  sandbox: *validator_audit_output
  simulation: *validator_audit_output

Thresholds and quality gates

  • At least one validator path must be independent of the target's defining assumptions.
  • Shared or derived-from-target dependencies must be explicit in the matrix.

Failure and counterexamples

Pass-by-construction is a finding, not evidence of corroboration. Unknown dependencies remain unresolved.

Provenance map

  • resolved: circular-validation-audit

Preserved source criteria ledger

sourcesource linekindsource criterion
v4 architecturenode desctextualBuild claim-validator assumption matrix and require a non-circular failure channel.

Context checkpoint / Delta notes

Append assumptions, matrix cells, circularity findings, and proposed independent test.

Mode branches

  • validator: inspect validator implementation assumptions.
  • benchmark: inspect benchmark construction and metric assumptions.
  • sandbox: inspect environment/oracle assumptions.
  • simulation: inspect simulator and initialization assumptions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free