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 HoangNguyen0403/agent-skills-standard --skill cyber-evidencegit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/cyber-evidence)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/cyber-evidence"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/cyber-evidence/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/hoangnguyen0403/agent-skills-standard/cyber-evidence"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/cyber-evidence.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 | $0.00044 | $0.00822 |
| Opus 5.5 | $0.00018 | $0.00329 |
| Sonnet 5.5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
cyber-evidence 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 yesterday.
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.
Cyber Evidence
Priority: P0 (CRITICAL)
Record what was observed, how it was sourced, and what remains unknown; never turn absence of proof into proof.
Structure
cyber-evidence/
├── SKILL.md
├── references/evidence-record.md
└── evals/evals.json
Workflow
- Bind record to
engagement_scope_ref,skill_version, andsource. - Capture
observed_at, observer, method, and evidence references; redact secrets and sensitive payloads. - For paired exercised-lab validation claims, attach optional
lab_validationextension with transitive binding chain:ObservationRecord.action_receipt_ref -> ActionReceipt.gate_ref -> GateDecision.request_ref -> ActionRequest. Unpaired analysis uses the base record directly. - Set exactly one
finding_status:confirmed,suspected,blocked,not-tested, orfalse-positive. Retain prior corroborated findings if a retest step blocks. - For paired defensive controls, set outcome:
blocked,prevented,detected,responded, ortelemetry-gap. - State limitations, missing controls, residual cleanup state, and accountable owner.
- Update canonical
artifacts/security-review.mdwhen a continuous workflow chain owns it. Base fields:engagement_scope_ref,skill_version,source,observed_at,finding_status,evidence_refs,limitations,accountable_owner. Optional metadata:observer,method,expected_observation,authorization_ref,redaction_note,independent_ground_truth_ref.
Rules
- Hashes and timestamps support provenance; they do not prove trusted origin or efficacy.
- Paired exercised-lab claims require complete transitive binding; ordinary source or supplied-evidence confirmation does not require host receipts.
- Retain corroborated confirmed or suspected findings across blocked retests; attempting a blocked retest never erases prior findings or forces them to not-tested (IR03).
- Default to
finding_status: not-testedonly when no supplied or exercised evidence exists (AC-CLV-11);blockedfinding denotes an evidence-backed barrier, not a mechanical step-state copy. - Failed reproduction does not prove vulnerability absence (AC-CLV-18); mark negative/insufficient, never
false-positivewithout independent invalidating evidence. - An exercised action without observation yields
telemetry-gap(AC-CLV-12). An observation alone cannot prove an action occurred. - Unverified or failed teardown must disclose
residualorunverifiedstate (AC-CLV-13); post-expiry teardown requires surviving authority. - Correlation key
(run_id, attempt_id, test_id)is immutable per attempt; conflicting or reused keys are rejected. - Keep raw evidence separate from sanitized reports; never persist credentials, real secrets, or unnecessary personal data.
- Promotion requires independent review; an operator cannot approve their own result.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +3 lines d0b37d14007c
- 28d ago First seen · 54 lines · 44 tokens per session scan A a2fae7eea83c
cyber-evidence is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (582 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 822 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 2026-09-30.
Other skills, from other repositories
nextjs-idioms
Next.js App Router architecture: React Server Components (RSC), Server Actions, nested layouts, route handlers, and streaming. Use when building or refactoring Next.js web applications. Pair with react-idioms and typescript-idioms.
react-idioms
React 19+ patterns: custom hooks, Suspense boundaries, state management, component composition, and web performance. Use when developing or refactoring React components and client applications. Pair with typescript-idioms.
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
oma-frontend
Implement or modify web UI in React, Next.js, or Angular. Use for components, pages, styles, forms, and frontend state or data flows.
design-patterns
Frontend design patterns with React 19.2 and TypeScript 6 examples (Composition, Compound Components, Custom Hooks, Render Props, HOC, State Machines). Use when user asks "implement pattern", "use composition", or when designing reusable components.
react-nextjs
React 19.2 + Next.js 16 development - Server Components, Cache Components, proxy.ts, View Transitions, App Router, TypeScript 6, and Tailwind CSS v4. Use when building frontend apps, creating components, or asking "how do I set up X?".