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 rsenna/rs-agent-plugin --skill repo-standardgit clone --depth 1 https://github.com/rsenna/rs-agent-pluginWrote 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/rsenna/rs-agent-plugin/repo-standard)<a href="https://agentmods.dev/skills/rsenna/rs-agent-plugin/repo-standard"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/repo-standard/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/rsenna/rs-agent-plugin/repo-standard"><img src="https://agentmods.dev/badge/skills/rsenna/rs-agent-plugin/repo-standard.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 | $0.00053 | $0.03158 |
| Opus 5 | $0.00026 | $0.01579 |
| Sonnet 5 | $0.00011 | $0.00632 |
| Haiku 4.5 | $0.00005 | $0.00316 |
Grade C, and why
repo-standard scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- TODO: how to get the repo running locally --> How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-standard
Checks (or creates) the documentation and folder artifacts required for a repo's declared stage tier, as defined in the cross-repo standard design doc.
Two modes — audit (read-only) and scaffold (non-destructive write).
The command plumbing is implemented in skills/repo-standard/repo-standard.sh.
Both fail closed if repo.toml is absent or stage is missing/invalid.
Prerequisites
- You must be inside a git repo with a
repo.tomlthat has a validstagefield. Bothauditandscaffoldfail closed — they stop with a clear error ifrepo.tomlis absent orstageis missing or not one of the four valid values. No default is inferred. - Valid
stagevalues:prototype,in-progress,released,archived. scaffoldnever overwrites existing content — only creates what is absent.
Workflow
audit — read-only compliance check
- Verify bootstrap: confirm
repo.tomlexists andstageis a valid value. If not, stop with a clear error — do not infer a default. - Read the stage from
repo.toml. - Diff against the required-paths table (see below). For each required path: check whether it exists. For
repo.tomlitself, also confirm thestage=line is present and valid. For.gitignore, existence isn't enough — verify the graphify block works, not that it merely contains certain text (see the### .gitignorestarter-content section below, "Audit behavior"). This is the one required path with a behavioral check, everywhere else stays presence-only. - Report missing required paths, note optional paths that are absent (for information only), and confirm what is already present. Output is human-readable; no files are created or modified.
scaffold — non-destructive creation
- Run the full
auditcheck first. Same bootstrap rules apply — fail closed on missing/invalidstage. - For each missing required path, offer to create it with minimal starter content (see starters below). Never overwrite a path that already exists, even if its content looks wrong — report it and move on.
- After creating files, print a summary of what was created vs what was skipped (already existed).
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.
- 5d ago Changed a67ad411748c
- 9d ago First seen · 246 lines · 53 tokens per session scan C a85ba1582ad2
repo-standard is a skill published in the GitHub repository rsenna/rs-agent-plugin (2 stars, last pushed 8d ago), licensed MIT. It adds 53 tokens to every session and 3,158 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). 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…