ratemy.sh

ratemyharness · Release review for agent runtimes

A demo is not evidence.

Your agent completed a demo. Now prove the runtime deserves real tools, data, and users — the loop, tool dispatch, context, permissions, and recovery around it, judged on evidence a skeptical engineer can check.

Audit · H-014 target: public-launch ref: sha256:9f3c…e2a1

Issue list

BLOCKER · H-002Cancellation does not stop tool calls — the agent keeps spending money after the user presses Stop.

HIGH · H-005Retry re-executes a non-idempotent transfer — one approval can charge twice.

To verify

UNKNOWN · U-003Tenant isolation has not been exercised — one user's data may reach another.

Evidence lanes

deterministic-checksPASS
critical-journey-e2eFAIL
probabilistic-evalUNVERIFIED
continuous-evidenceN/A — no deployment yet
Maximum safe target: internal-demo
Blocking gates: runaway-execution, duplicate-irreversible-effect
NOT READY

Scope

What it actually audits.

Only what has a product consequence. Style preferences and fashionable architecture are not findings.

·

Zero-tolerance runtime invariants: authority, tool-call correlation, isolation, idempotency, termination, truthful state.

·

Probabilistic task quality: repeated success, unsafe outcomes, variance, latency, and cost per successful task.

·

Context ordering, provenance, truncation, persistent state, memory, and session isolation.

·

Timeouts, retry budgets, cancellation, checkpoints, resume, and deterministic termination.

·

Permissions, sandboxing, approvals, untrusted input, secrets, network, and tenant boundaries.

·

Queues, backpressure, tracing, incident recovery — and for public targets, drift, canaries, and rollback.

·

Measurable task uplift over the simplest credible plain-loop or previous-runtime baseline.

With and without

What changes once it is installed.

A capable agent already reviews code. These are the behaviors that appear only with the Skill loaded.

Without it

It blames “the model” and suggests a better prompt.

With it

It separates the model choosing an action, the loop repeating it, and the harness enforcing controls — then finds cancellation received but never propagated.

Without it

It recommends adding retries with backoff.

With it

It distinguishes a model or tool-call ID from an end-to-end idempotency key the side-effect owner actually accepts, and traces effect-commit-then-timeout-then-retry.

Without it

It carries that text into high-authority context and acts on it.

With it

It refuses the payload and maps the trust boundary from tool output through context into the dispatcher.

Without it

Architectural sophistication and green CI read as behavioral value.

With it

It states plainly that repository CI and valid fixtures are structural checks, never proof that the harness behaved correctly.

Both columns come from the Skill's own test cases — what it requires of itself, not a score anyone measured. The paired runs are written down but have not been executed, so if you want the number rather than the promise, run them: evals/execution_cases.json.

How it runs

Two settings, then evidence.

It never silently defaults to the strictest review — or the friendliest.

1

Reviewer setting

Agent product owner / Staff agent-runtime engineer / Red-team reviewer / SRE-operator / Oral-defense professor

2

Review degree

Quick check / Strict review / Release gate / Privileged review / Life-or-death

§

No score averages away a veto.

Hard gates block the release regardless of the weighted average. Accepting the risk does not turn an active gate into a technical pass.

§

A plausible diff is not a fix.

Findings advance to verified-fixed only on fresh passing evidence from an independent retest that also audits the fix code itself.

The five

One evidence contract, five layers.

Each is a standalone plugin. Install only the layer you are shipping.

Install

One repository, three clients.

Pick one method per client and scope. The first audit runs read-only — your sandbox, permissions, and approvals stay the security boundary.

Claude Code
/plugin marketplace add \
  AmsonntagChow/ratemyharness
/plugin install \
  ratemyharness@amsonntagchow-ratemyharness
Codex
codex plugin marketplace add \
  AmsonntagChow/ratemyharness
codex plugin add \
  ratemyharness@ratemyharness
Any Skills client
npx skills add \
  AmsonntagChow/ratemyharness \
  --skill ratemyharness