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 skills add ocentra/ocentra-enforcer --skill security-testinggit clone --depth 1 https://github.com/ocentra/ocentra-enforcerWrote 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/ocentra/ocentra-enforcer/security-testing)<a href="https://agentmods.dev/skills/ocentra/ocentra-enforcer/security-testing"><img src="https://agentmods.dev/badge/skills/ocentra/ocentra-enforcer/security-testing/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/ocentra/ocentra-enforcer/security-testing"><img src="https://agentmods.dev/badge/skills/ocentra/ocentra-enforcer/security-testing.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 | $0.00062 | $0.01283 |
| Opus 5.5 | $0.00025 | $0.00513 |
| Sonnet 5.5 | $0.00012 | $0.00257 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
security-testing 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Testing (Money-Critical Mandate)
tier: "T3 advisory — no mechanization possible: this SKILL sequences human/agent judgment across
Track H (h01-h07); it produces no Finding and gates nothing. Mechanized enforcement lives in the
h01-h07 Rust Validator rows and the profiles/money-critical-security.json profile, not here."
stages: "route -> h01 classify -> h02 required-categories -> h03 threat-map -> h05 invariants -> h06 mechanics -> h07 tooling/CI"
domain: "GENERIC: any system handling money/payments/value behind untrusted infra (Cloudflare/AWS/API
gateways are NOT security boundaries; internal APIs are hostile). NOT game- or crypto-specific;
crypto/blockchain is one OPTIONAL instance, never assumed."
doctrine: "AI output is untrusted input. Silence != permission. If a change cannot be proven safe
under adversarial conditions, it is unsafe. AI cannot waive/simplify/remove tests or downgrade
security tests to unit tests."
mechanized_home: "profiles/money-critical-security.json (neutral, no branding) + crates/enforcer-security/src/policy_ingest.rs (ingest a project's own spec into that profile shape)"
This SKILL is prose walkthrough, not an enforcement engine. It carries the
label above deliberately: nothing in this file emits a Finding, and
nothing in this file gates a merge. The T1/T2 mechanized gates live in the
Track H Validator rows (crates/enforcer-security/src/rules/*.rs) and the
loadable profile (profiles/money-critical-security.json). Use this SKILL
to decide WHICH of those gates apply to the change in front of you, in
order.
When To Use This
Any change that creates, transfers, modifies, or destroys value; triggers a blockchain instruction; signs a message; computes an economic/reward/credit/ balance/cooldown value; performs a rollback or compensation; depends on time-based state; or touches a kill switch. If unsure whether a unit is money-critical, treat it as money-critical (fail-closed default, doctrine §8.2).
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.
- 1mo ago First seen · 92 lines · 62 tokens per session scan A d608f8d4cf88
security-testing is a skill published in the GitHub repository ocentra/ocentra-enforcer (0 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,283 once invoked, about $0.0002 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 2026-08-31.
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.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
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".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
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.