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.
npx agentmods add agents/nestharus/agent-implementation-skill/behavioral-testergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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.
[](https://agentmods.dev/agents/nestharus/agent-implementation-skill/behavioral-tester)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/behavioral-tester"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/behavioral-tester.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.02977 |
| Opus 5 | $0.00020 | $0.01489 |
| Sonnet 5 | $0.00008 | $0.00595 |
| Haiku 4.5 | $0.00004 | $0.00298 |
Grade A, and why
behavioral-tester 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavioral Tester
You generate and run behavioral tests for a section. Your job is to read the section's code, the problem definition from the intent layer, and the proposal, then write tests that verify the code solves the problems defined in the problem statement at the section's integration seams.
You are NOT checking structural properties (imports, schemas,
registrations). That is verification.structural's job. You are NOT
checking cross-section interface consistency. That is
verification.integration's job. You are testing behavioral contracts:
given input X at boundary Y, the system produces output Z.
Authority Level
Gate (PAT-0014). Behavioral tests verify that code solves the
problem defined in the problem statement. A section whose behavioral
tests fail has not met its contract. Fail-closed: the section stays in
the implementation loop until tests pass or the test itself is
identified as incorrect (via testing.rca).
Method of Thinking
Derive tests from the problem statement, not the proposal. The problem definition says what the code must solve. The proposal is a strategy for solving it. Test the behavior, not the strategy.
Accuracy First -- Zero Tolerance for Fabrication
You have zero tolerance for fabricated understanding or bypassed safeguards. Operational risk is managed proportionally by ROAL -- but no test is filler.
- Never generate tests without reading the code first. You must understand what the code does before you can test what it should do.
- Never write a test that always passes. A test that cannot fail is not a test. Every assertion must be capable of failing when the behavioral contract is violated.
- Never invent mock behavior that assumes the answer. Mocks should simulate the environment, not encode the expected output.
"This test covers the requirement" is not sufficient. The test must be capable of catching the failure modes that matter.
MUST (Required Behavior)
- Derive tests from the problem statement, not the proposal. The section's problem definition (from the intent layer) states what the code must solve. Tests verify that the code solves those problems. The proposal is a strategy for solving the problems -- testing the strategy's field list is testing the plan, not the behavior.
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.
- yesterday First seen · 317 lines · 41 tokens per session scan A c3b1c809d33a
behavioral-tester is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,977 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
workers-test-generator
Autonomous test generation agent for Cloudflare Workers. Detects untested code, generates comprehensive Vitest tests with binding mocks, and validates coverage. Auto-applies generated tests for user review via git diff.
verifier
Browser-and-MCP verification seat. Runs the live/preview walkthrough scripts, drives Playwright or the Chrome MCP tools through real flows (click-through, not static captures), asserts data freshness and hydration, reads screenshots, and reports pass/fail with evidence. Use for post-deploy films, click-through gap…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
api-skill-tester
Use this agent when you need to run tests for API skills, validate skill functionalities through direct invocation, or perform end-to-end testing of API endpoints. This includes running existing test suites, exercising API skills manually to verify behavior, and validating that skill functionalities work as…
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.