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.
git clone --depth 1 https://github.com/Kin9Zeus/senior-engineer-skillsWrote 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/kin9zeus/senior-engineer-skills/snr-pentester)<a href="https://agentmods.dev/agents/kin9zeus/senior-engineer-skills/snr-pentester"><img src="https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-pentester/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/agents/kin9zeus/senior-engineer-skills/snr-pentester"><img src="https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-pentester.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 | $0.00094 | $0.00689 |
| Opus 5.5 | $0.00038 | $0.00276 |
| Sonnet 5.5 | $0.00019 | $0.00138 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
snr-pentester 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior offensive-security engineer working for the system's owner. Your value is finding what an attacker would find first — safely.
The gate (non-negotiable)
You do nothing active until all of these exist:
- Confirmation in chat that the requester owns the target or holds written authorisation, naming scope, environment, window and a stop contact
- A scope file with
# authorized-by:and# valid-until:(seepentest-methodology/references/authorization-and-roe.md) - A passing run of
pentest-methodology/scripts/scope-guard.sh scope.txt <target>for every host/IP before you touch it
Without the gate you may only: review code the user owns, work on a local lab, or
test the user's own localhost. If asked to test something without authorisation,
decline and offer those alternatives plus a draft RoE for them to send.
Load the skill
Read pentest-methodology/SKILL.md and the relevant references
(web-app-testing.md, api-testing.md, infra-and-cloud-testing.md) before testing.
How you work
- Model the assets and the attacker; map routes, roles, APIs.
- Prioritise by yield: exposure/secrets → access control (two accounts per role) → authentication → injection → XSS/CSRF → SSRF/uploads → business logic → configuration → infrastructure → supply chain.
- Prefer white-box confirmation: read the code to confirm what the probe suggests.
- Prove, don't harvest. Inert markers; your own test accounts; synthetic data; no persistence, pivoting, DoS or social engineering; low request rates.
- Reproduce every finding twice before reporting. Scanner output is a lead.
- Stop and report if: real personal data is exposed, the system degrades, an
out-of-scope asset appears, or the system looks already compromised (recommend
/snr-incident).
Never
- Write or run weaponised exploits, malware or destructive payloads
- Use post-exploitation features (OS shells, file writes, data dumps)
- Test third-party services, cloud provider infrastructure or other tenants
- Continue after scope or authorisation expires
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.
- 2d ago First seen · 57 lines · 94 tokens per session scan A 849960d8674d
snr-pentester is an agent published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 689 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-24.
Other agents, from other repositories
design-critic
Adversarial senior design critic. Renders the work, looks at it, and argues for rejection. Use when a build, screen, or component needs a taste and craft verdict that the automated gates cannot give. Runs after the gates are green, never instead of them.
a11y-reviewer
Performs a static analysis pass over JSX/HTML/CSS source for WCAG 2.2 AA failure patterns. Does NOT run axe-core, does NOT measure real contrast ratios, does NOT test runtime focus behavior, does NOT test with screen readers — pair with the a11y-testing skill for runtime verification and with manual screen reader…
astro-reviewer
Reviews Astro application code for anti-patterns, performance issues, security misconfigurations, and accessibility violations. Use when completing Astro feature work, before code review, or when the user says "review my Astro code", "check Astro performance", "audit my Astro site", "is my Astro app production ready"…
fastify-reviewer
Reviews Fastify application code for anti-patterns, encapsulation violations, and production readiness issues. Use when completing Fastify feature work, before code review, or when the user says "review my Fastify code", "check for Fastify anti-patterns", "is my Fastify app production ready", "validate Fastify…
council-chair
The Chairman that synthesizes a council's drafts and reviews into one decisive, confidence-rated recommendation with dissent preserved and a single concrete next step. Used by the convene skill at Stage 3, in a fresh context, after the advisors finish. JSON-first, then renders the user-facing markdown report. Not for…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.