---
name: behavior-validator
description: "Source-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts."
title: behavior-validator
canonical_url: https://skilld.dev/gh/openclaw/agent-skills/behavior-validator
last_updated: 2026-09-30T03:34:37.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [agents/openai.yaml](https://skilld.dev/api/skills-raw/openclaw/agent-skills/behavior-validator/agents/openai.yaml), [references/contract-template.md](https://skilld.dev/api/skills-raw/openclaw/agent-skills/behavior-validator/references/contract-template.md), [references/report-schema.md](https://skilld.dev/api/skills-raw/openclaw/agent-skills/behavior-validator/references/report-schema.md).
>
> If the user asked to install this Skill, run `npx skilld install openclaw/agent-skills/behavior-validator`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/behavior-validator`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/openclaw/agent-skills/behavior-validator) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/behavior-validator`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/behavior-validator --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/behavior-validator --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Behavior Validator

Validate observable behavior without inspecting source. Use this as the black-box companion to code-aware review: `autoreview` judges the change bundle, while `behavior-validator` judges the running product, CLI, API, or generated artifact against a behavior contract.

## Contract

- Read the behavior contract first. If none exists, write a short one from the user request before testing. See `references/contract-template.md`.
- Stay source-blind. Do not inspect source files, diffs, tests, git history, implementation notes, build internals, or review bundles.
- Interact only through user-visible or operator-visible surfaces: browser, CLI, API, generated files, public logs, screenshots, accessibility trees, or documented runtime output.
- Treat implementation-looking evidence as contamination. If source access is required to continue, stop and report `blocked_source_required`.
- Report findings against contract clauses and observable steps, not code locations.
- Do not mark a workflow as passing until each relevant contract clause is pass, fail, blocked, or out of scope.

## Isolation

Prefer a source-blind workspace:

```sh
validator_dir="$(mktemp -d "${TMPDIR:-/tmp}/behavior-validator-run.XXXXXX")"
chmod 700 "$validator_dir"
cp behavior-contract.md "$validator_dir/"
cd "$validator_dir"
```

Launch or connect to the target from the contract. Keep only the contract, allowed fixtures, and redacted captured evidence in the private validator workspace. Supply credentials through approved secret tooling or exact environment variables; never copy credential values into the workspace, report, screenshots, or logs. Do not use fixed shared paths for contracts or captured evidence. If the app must be started from the source checkout, start it from a separate terminal and do not read source while validating.

## Workflow

1. Parse the contract into user tasks, expected behavior, anti-cheat probes, setup, and evidence requirements.
2. Prepare runtime access: target URL, CLI command, API endpoint, fixture data, credentials, or generated artifact path.
3. Exercise each user task as a real user or operator would.
4. Run anti-cheat probes: vary fixture data, refresh/retry, test empty and invalid inputs, verify persistence, inspect generated output, and confirm buttons/commands perform real work rather than only displaying success text.
5. Capture evidence as compact redacted notes, screenshots, terminal excerpts, response summaries, file summaries, or accessibility observations. Omit credentials, tokens, cookies, private user data, and unrelated log content.
6. Emit a structured report. Use `references/report-schema.md` when a machine-readable report is useful.
7. If the orchestrator fixes a finding, rerun only the affected contract clauses plus any nearby regression probes.

## Finding Rules

- Fail when observable behavior violates the contract, a task cannot be completed, expected state is fake/static, or evidence is insufficient for a claimed pass.
- Block when required runtime access, credentials, fixtures, network, or tools are missing.
- Mark out of scope only when the contract explicitly excludes the behavior or the task depends on a user-owned product decision.
- Reject purely aesthetic, code-quality, or implementation-style concerns; those belong to code-aware review.

## Final Report

Include:

- target exercised
- contract file or inline contract used
- pass/fail/blocked/out-of-scope summary
- accepted behavioral findings with reproduction steps and evidence
- anti-cheat probes run
- remaining blockers, if any
