behavioral-acceptance-review

behavioral-acceptance-review is a skill for Claude Code, Codex from a1024053774/design-integrity-guardrails. It costs 50 tokens per session (716 once invoked), scanned A, original, MIT.

A review skill that checks whether claimed behavior has independent evidence from tests, evaluations, benchmarks, generated files, public interfaces, or user workflows. It acts as an acceptance auditor at a completion checkpoint.

In plain words
What is it for?
It is for reviewing whether completion claims are supported by trustworthy tests and real boundary evidence, without changing the implementation.
Why use it?
It helps detect cases where a green test or mocked system does not actually prove the behavior users or external systems depend on.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing whether completion claims are supported by trustworthy tests and real boundary evidence, without changing the implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add a1024053774/design-integrity-guardrails --skill behavioral-acceptance-review
Clone the repo
git clone --depth 1 https://github.com/a1024053774/design-integrity-guardrails

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for behavioral-acceptance-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review/github.svg)](https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review)
Your own site
<a href="https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review"><img src="https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for behavioral-acceptance-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review"><img src="https://agentmods.dev/badge/skills/a1024053774/design-integrity-guardrails/behavioral-acceptance-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.00716
Opus 5 $0.00025 $0.00358
Sonnet 5 $0.00010 $0.00143
Haiku 4.5 $0.00005 $0.00072

Measured 11d ago against content hash 8322652004fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

behavioral-acceptance-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

behavioral-acceptance-review/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Behavioral Acceptance Review

Act as an acceptance auditor, not the implementation agent, test author, or general code reviewer. Review one frozen candidate snapshot in a fresh, read-only context. Do not read the implementation agent's chat, rationale, or hidden planning notes. Do not edit files, tests, fixtures, branches, commits, deployments, or external systems.

When the claimed behavior depends on a domain rule, a real external boundary, timing, data semantics, permissions, deployment, or another condition that a mock cannot establish, require evidence from that boundary (or clearly mark the result INCOMPLETE). A host mock or simulator may prove pure logic, but it is not independent evidence of the boundary it replaces. Coordinate with the reality-first-engineering gate; do not recreate its ledger or turn this review into a second architecture exercise.

Establish independence

Rebuild the acceptance criteria from the user's task, public contract, and inputs external to the implementation. Tests added or modified in the current change are untrusted evidence, not the oracle. Inspect them for leakage, but do not accept a green suite as the only proof.

Check that:

  1. The test observes the real public or user-visible entry point.
  2. Inputs are supplied outside production code and are not copied into it.
  3. Expected values and oracles do not import or duplicate production constants, helpers, templates, or generated answers.
  4. At least one unseen, metamorphic, or sentinel input is exercised.
  5. A known-bad implementation would fail: hard-coded output, ignored input, always-success/empty output, or a test-only branch.
  6. Assertions prove the claimed behavior rather than replaying one fixed example or weakening the requirement.
  7. For generated text or artifacts, structure, provenance, input dependence, and required fields are checked; exact prose snapshots alone are insufficient.

For autoresearch, benchmark, evaluation, or generation tasks, change one input field such as title, domain, chapter, or a nonce and verify that the corresponding output changes. If a constant-output implementation can pass, the test is not an acceptance test.

Read the full file on GitHub · 70 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 70 lines · 50 tokens per session scan A 8322652004fe

Subscribe to this mod's changes

behavioral-acceptance-review is a skill published in the GitHub repository a1024053774/design-integrity-guardrails (0 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 716 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories