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 travisbergen2/rpcs1-sdk --skill rpcs1-translation-layergit clone --depth 1 https://github.com/travisbergen2/rpcs1-sdkWrote 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/travisbergen2/rpcs1-sdk/rpcs1-translation-layer)<a href="https://agentmods.dev/skills/travisbergen2/rpcs1-sdk/rpcs1-translation-layer"><img src="https://agentmods.dev/badge/skills/travisbergen2/rpcs1-sdk/rpcs1-translation-layer/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/travisbergen2/rpcs1-sdk/rpcs1-translation-layer"><img src="https://agentmods.dev/badge/skills/travisbergen2/rpcs1-sdk/rpcs1-translation-layer.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 | $0.00065 | $0.01336 |
| Opus 5 | $0.00032 | $0.00668 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
rpcs1-translation-layer 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 10d 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.
High-Fidelity Human-AI Translation Protocol (HF-HATP) v2.0
Engineering specification for high-fidelity human-AI interpretation. v2.0 is generated from the shipped implementation in @rpcs1/core and replaces every v1.9 package.
Deprecation rule: any SKILL.md using bare factor names
IC / UE / EC / NM / SG / TIis a stale v1.9 copy — delete it. Those abbreviations collided with the RPCS-1 receiver primitives (TI, SG, UE) and were renamed in the implementation.
Core Principles
- Vocabulary Asymmetry: Human language compresses meaning; AI expands it.
- Immutability of Literal Request: Inferences augment but NEVER replace original input.
- Ambiguity vs. Uncertainty:
- Ambiguity: multiple valid interpretations exist (high margin risk).
- Uncertainty: single interpretation with low evidence/confidence.
- Receiver Matching (new in v2.0): output is rendered for the specific human's receiver profile, not a lumped audience style. Fixed styles ("neurodivergent-explicit" etc.) are retired.
- Adaptive Learning: profiles update from observed corrections, governed by the user's own Update Elasticity.
The Receiver Profile — R̂(user)
Five RPCS-1 receiver primitives, each on a [0, 100] scale (ReceiverProfile):
| Primitive | Meaning |
|---|---|
| TI — Temporal Integration | how much history the receiver integrates |
| SG — Signal Gain | how strongly incoming signals are amplified |
| FT — Filtering Threshold | how conservatively action is gated |
| UE — Update Elasticity | how readily the model is revised |
| AR — Ambiguity Resolution | how aggressively uncertainty is resolved |
- Calibrated by the 5-item intake (
scoreIntake), one item per primitive. - Mapped to concrete
RenderingDirectives: structure (bluf/balanced/context_first), warmth (minimal/moderate/warm), explicitness (explicit_literal/moderate/implication_ok), revision posture (consistent/balanced/open_challenge), ambiguity handling (clarify/commit_with_note/commit). - Refined online by
updateProfile(step size governed by the profile's own UE — a rigid profile resists being rewritten by one bad day). profileDivergencecompares self-reported vs. observed behavior (the "masking mirror").
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.
- 10d ago First seen · 92 lines · 65 tokens per session scan A 0eeb2cc5b268
rpcs1-translation-layer is a skill published in the GitHub repository travisbergen2/rpcs1-sdk (0 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,336 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…