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/transilienceai/communitytools/dynamic-testergit clone --depth 1 https://github.com/transilienceai/communitytoolsWrote 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/transilienceai/communitytools/dynamic-tester)<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>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 | $0.00073 | $0.00571 |
| Opus 5 | $0.00036 | $0.00285 |
| Sonnet 5 | $0.00015 | $0.00114 |
| Haiku 4.5 | $0.00007 | $0.00057 |
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.
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
- Confirm the running instance + authorization from
engagement-scope.json; load creds viapython3 tools/env-reader.py <NAMES>. - 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.
- Capture evidence as
evidence_type: dynamic_observation— the request/response or command/output, with the file it was written to assource_file, asource_linenoif applicable (the log line), and the verbatimquoted_textthe verifier can grep. Save raw transcripts under${OUTPUT_DIR}/findings/<id>/evidence/. - 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.
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.
- 5d ago First seen · 31 lines · 73 tokens per session scan A a07d8d7518ef
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.
Other agents, from other repositories
grow-agent
Session orchestrator for one domain. Owns Rule 20a session-start gate + Rule 4 goal-driven loop + Rule 22 decision compaction + Rule 21 checkpointing. Promotes confirmed cross-target patterns into KB/skill proposals. On-demand only.
finding-verifier
Re-verify suspected/confirmed findings and investigate anomalies. Promotes states (suspected → confirmed) or demotes (→ stale / likelyfalsepositive).
auth-payment-agent
Deep-dive OAuth/OIDC, WebAuthn/FIDO2/passkeys, Apple/Google/Samsung Pay, IAP receipt validation, 3DS 2.x bypass, SCA exemption abuse, recovery downgrades. $5k-$50k bug class.
mobile-dynamic-agent
Drive Frida (iOS+Android) and adb (Android) on operator's host. Bypass SSL pinning + root/JB detection, hook crypto/storage, abuse exported components and deep links. Dynamic-only; no static decompile.
recon-agent
Map a target's attack surface — endpoints, tech stack, sensitive files, hidden parameters. Returns enriched intel for the orchestrator.
vuln-scanner
Test ONE vulnerability category on assigned non-overlapping endpoints. Returns findings + anomalies for orchestrator review.