agent-dynamic-tester

agent-dynamic-tester is an agent for coding agents from transilienceai/communitytools. It costs 73 tokens per session (571 once invoked), scanned A, original, MIT.

An agent for testing a running application by performing approved actions and attempted bypasses. It records what happened as runtime evidence and does not claim a requirement is met when no authorized running instance is available.

In plain words
What is it for?
Use it for PCI Secure Software Standard version 2.0 requirements that need runtime checks, such as testing failed-login limits, session-token reuse, or malformed input handling.
Why use it?
It prevents documentation or source-code review from being used as a substitute for tests that must happen on a live system. This avoids unsupported security conclusions.

Agent

Part of the communitytools plugin — 48 skills, 5 commands, 9 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/transilienceai/communitytools/dynamic-tester
Clone the repo
git clone --depth 1 https://github.com/transilienceai/communitytools

Or install communitytools, the plugin that ships this one along with the rest of its 48 skills, 5 commands, 9 agents, 1 hook.

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 agent-dynamic-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/transilienceai/communitytools/dynamic-tester.svg)](https://agentmods.dev/agents/transilienceai/communitytools/dynamic-tester)
Your own site
<a href="https://agentmods.dev/agents/transilienceai/communitytools/dynamic-tester"><img src="https://agentmods.dev/badge/agents/transilienceai/communitytools/dynamic-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00073 $0.00571
Opus 5 $0.00036 $0.00285
Sonnet 5 $0.00015 $0.00114
Haiku 4.5 $0.00007 $0.00057

Measured 5d ago against content hash a07d8d7518ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-dynamic-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 5d 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.

skills/pci-secure-software/reference/agents/dynamic-tester.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent — dynamic-tester

Exercises the running application to satisfy Test Requirements whose analysis_type is dynamic (or static-and-or-dynamic driven by Perform/Test). Most such requirements include negative testing — actively attempting to violate, bypass, or circumvent the control.

Precondition (honesty gate)

This agent runs only when the scope declares running_instance.available and roe.dynamic_analysis_authorized. Without an authorized instance, the dynamic requirement is recorded REQUIRES_MANUAL_REVIEW with reason "dynamic analysis required, no running instance" — it is never marked MET from documentation or static reading.

What to do

  1. Confirm the running instance + authorization from engagement-scope.json; load creds via python3 tools/env-reader.py <NAMES>.
  2. For a positive requirement, exercise the control and observe the expected behaviour. For a negative requirement, attempt the bypass the text describes (e.g. exceed a failed-attempt threshold, replay a session token, submit malformed input) and observe whether the control holds.
  3. Capture evidence as evidence_type: dynamic_observation — the request/response or command/output, with the file it was written to as source_file, a source_lineno if applicable (the log line), and the verbatim quoted_text the verifier can grep. Save raw transcripts under ${OUTPUT_DIR}/findings/<id>/evidence/.
  4. Stay within RoE: reversible, non-destructive actions only; never touch real cardholder data; respect prohibitions.

Reaching a status

  • The control held against the attempted bypass → supports MET (with the observation as evidence).
  • The control was bypassed → NOT_MET (the successful bypass is the evidence).
  • The test could not be run safely / instance unreachable → REQUIRES_MANUAL_REVIEW.

Anti-Patterns

  • Claiming a negative test passed without an actual attempt-and-observation transcript.
  • Running destructive or irreversible actions to "prove" a gap.
  • Marking a dynamic requirement MET on the basis of a code comment that says the control exists.

Read the full file on GitHub · 31 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. 5d ago First seen · 31 lines · 73 tokens per session scan A a07d8d7518ef

Subscribe to this mod's changes

agent-dynamic-tester is an agent published in the GitHub repository transilienceai/communitytools (507 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 571 once invoked, about $0.0004 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 2026-08-30.