Borrowing it
Nothing to install: this file belongs to ivanprytula/cv-rest-mcp-server. 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/ivanprytula/cv-rest-mcp-server/main/.github/skills/across/SKILL.mdgit clone --depth 1 https://github.com/ivanprytula/cv-rest-mcp-serverWrote 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/ivanprytula/cv-rest-mcp-server/across)<a href="https://agentmods.dev/skills/ivanprytula/cv-rest-mcp-server/across"><img src="https://agentmods.dev/badge/skills/ivanprytula/cv-rest-mcp-server/across/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/ivanprytula/cv-rest-mcp-server/across"><img src="https://agentmods.dev/badge/skills/ivanprytula/cv-rest-mcp-server/across.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 | $0.00032 | $0.00401 |
| Opus 5 | $0.00016 | $0.00200 |
| Sonnet 5 | $0.00006 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
across 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 8d 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.
What it actually says
ACROSS Design Principles
Apply these principles when writing, reviewing, or refactoring code.
A - Abstractions and Decomposition
- Extract an interface or protocol only when consumers need different implementations.
- Give each module a defined responsibility and an explicit contract.
- Separate lifecycle management from business logic.
- Use a facade when callers would otherwise coordinate several internal steps.
C - Composition by Default
- Prefer composition and injected collaborators over inheritance.
- Use inheritance only for intentional extension points.
- Prefer a plain function or protocol over a base class when either is sufficient.
- Extract a helper instead of creating a base class solely to share methods.
R - Escape the Rabbit Hole
- Define the scope, success metric, and stopping point before refactoring.
- Keep changes focused on the requested behavior.
- Split very large methods, but avoid replacing one understandable function with a deep call chain.
- Iterate in short cycles: edit, test, and reassess.
O - Optimize for Change
- Keep business-rule changes local, safe, and reversible.
- Add an adapter and registration point rather than changing shared contracts for each new integration.
- Use expand-contract for migrations and feature flags for risky behavior changes.
- Keep third-party SDK types behind project-owned interfaces.
S - Simple As Possible
- Match the solution to today's requirements.
- Generalize after the third real occurrence, not before.
- Do not add abstractions merely for testability or hypothetical future extensions.
- Prefer a small working function over a hierarchy that adds no useful variation.
S - Screaming Contract
- Name functions and classes with domain verbs.
- Use domain language in API endpoints and events.
- Prefer typed outcomes or specific exceptions over ambiguous booleans and generic errors.
- Make error messages describe the domain problem.
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.
- 8d ago First seen · 51 lines · 32 tokens per session scan A 06a9dd318d99
across is a skill published in the GitHub repository ivanprytula/cv-rest-mcp-server (0 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 401 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…