Borrowing it
Nothing to install: this file belongs to brovar/10x-pentest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/brovar/10x-pentest/main/.github/skills/pt-dynamic-plan/SKILL.mdgit clone --depth 1 https://github.com/brovar/10x-pentestWrote 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/skills/brovar/10x-pentest/pt-dynamic-plan)<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-dynamic-plan"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-dynamic-plan/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.
<a href="https://agentmods.dev/skills/brovar/10x-pentest/pt-dynamic-plan"><img src="https://agentmods.dev/badge/skills/brovar/10x-pentest/pt-dynamic-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00157 | $0.02190 |
| Opus 5 | $0.00078 | $0.01095 |
| Sonnet 5 | $0.00031 | $0.00438 |
| Haiku 4.5 | $0.00016 | $0.00219 |
Grade A, and why
pt-dynamic-plan 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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pt-dynamic-plan — Dynamic Test Runbook (Stage 4)
Build dynamic/test-plan.md — the runbook the human executes — per
foundation/dynamic-test-plan-schema.md. For each in-scope dynamic/both objective (and each code
Potential flagged verify-dynamically), select tools by the target class and write a concrete test
case: exact command, safety class, what to capture, and the fixed evidence path. The agent never
runs tools against the target — it emits commands; the human runs them. Tool selection from
target_classes is where technology-independence is realised.
When to use, when to skip
- Use after the threat model (black-box) or after code review (white/grey-box) to produce the runbook.
- Refresh (
--refresh) mid-engagement when new findings, objectives, orverify-dynamicallyPotentials have appeared — it appends only the new cases for the coverage gap (idempotent; an empty gap is a no-op). - Skip on re-entry when analysis has already appended the follow-up cases you need — just run
those. Don't re-plan cases already
run/analyzed.
Execution mode is downstream, not here
The plan is pure intent — identical whether a human runs it or the local agent /pt-dynamic-run
executes it (the two are interchangeable at the dynamic/evidence/<TC>/ seam). Plan registry-blind
by default; don't let machine state shape the runbook. Two optional aids for the local-executor path:
--prefer-available biases tool selection toward what environment/tool-registry.md marks available;
emitting the optional args block per case (alongside command) makes a case routable to a docker/MCP
backend. Neither changes the manual path. See METHODOLOGY.md §11.
Initial Response
- With
<engagement-id>(optionally--prefer-available,--refresh): proceed to Step 0. - Without: print
Usage: /pt-dynamic-plan <engagement-id> [--prefer-available] [--refresh].and STOP.
Inputs
attack-surface.md— [blocking].test-objectives.md— [blocking] (dynamic/bothrows, in priority order).target-profile.md— [blocking] (drives tool selection viatarget_classes).scope.md— [blocking] (RoE —destructive_policycaps every case; in-scope-only).- Code findings flagged
verify-dynamically— [optional]. foundation/tool-catalog.md— [optional] (per-class tools + example commands + safety notes).
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.
- 9d ago First seen · 134 lines · 0 tokens per session scan A 1ad9d5fe57f4
pt-dynamic-plan is a skill published in the GitHub repository brovar/10x-pentest (3 stars, last pushed 27d ago), licensed Apache-2.0. It adds 157 tokens to every session and 2,190 once invoked, about $0.0008 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.