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 getkyo/kyo --skill readme-analyze-existinggit clone --depth 1 https://github.com/getkyo/kyoWrote 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/getkyo/kyo/readme-analyze-existing)<a href="https://agentmods.dev/skills/getkyo/kyo/readme-analyze-existing"><img src="https://agentmods.dev/badge/skills/getkyo/kyo/readme-analyze-existing/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/getkyo/kyo/readme-analyze-existing"><img src="https://agentmods.dev/badge/skills/getkyo/kyo/readme-analyze-existing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.02113 |
| Opus 5 | $0.00039 | $0.01056 |
| Sonnet 5 | $0.00016 | $0.00423 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
readme-analyze-existing 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
readme-analyze-existing
Input: an existing README and the structured output of readme-analyze-source (spine candidate, callouts, API inventory).
Output: a structured action list consumed by readme-edit. Every action is one of: [CUT], [RELOCATE], [RESTRUCTURE], [REWRITE-HEADING], [REORDER], [ADD-CALLOUT]. Each entry names the line range it targets, the rationale (one sentence), and the replacement or destination.
This skill does NOT edit the README; it produces the diagnosis. readme-edit applies the actions. Keeping diagnosis and application separate prevents the common failure mode where an agent edits as it diagnoses and produces inconsistent or partial output.
Anchoring-bias mitigation (the 0(a)(i)/0(a)(ii) split)
A naive cleanup agent reads the existing README first, then proposes the spine, then evaluates the existing structure. This anchors the proposed spine on the existing README's wording. The fix: produce the spine BEFORE reading the existing README, then compare.
You must do these steps in this order:
- Step 0(a)(i): source-only spine. Already done by
readme-analyze-source— it produced the spine candidate without ever reading the existing README. Use that spine as the unbiased reference. - Step 0(a)(ii): comparison. Now read the existing README. Compare its opening to the source-only spine. The spine differential drives the cleanup actions.
If the existing README's spine ALREADY matches the source-only spine, you write FEWER actions. The cleanup target is the deviation from the source-only spine, not a fixed-percentage cut.
Action types and semantics
| Type | When to use | Required fields |
|---|---|---|
[CUT] |
The lines are noise, banned phrases, em-dashes, audience disclaimers, marketing copy, redundant prose with no curriculum value. | lines: A-B, rationale: <one sentence> |
[RELOCATE] |
The lines contain content that belongs elsewhere in the README (buried spine, misplaced callout). | lines: A-B, target: <line N, or 'after heading X'>, rationale: <one sentence> |
[RESTRUCTURE] |
The lines need replacement with a description-of-replacement (synthesize a spine from buried fragments; reshape a list into hooks). | lines: A-B, rationale: <one sentence>, replacement_description: <what to synthesize, sourced from where> |
[REWRITE-HEADING] |
A heading is generic or misleading and should reflect the section's actual content. | line: N, current: <text>, proposed: <text> |
[REORDER] |
A whole ## section is in the wrong curriculum position. |
from_line: N, to_line: M (move section starting at N to immediately before section at M), rationale: <one sentence> |
[ADD-CALLOUT] |
A surface in the inventory has a callout candidate but no inline qualifier in the README. | at_line: N, source_ref: <file:line>, text: <one or two sentences> |
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 · 131 lines · 78 tokens per session scan A 617ff326a427
readme-analyze-existing is a skill published in the GitHub repository getkyo/kyo (812 stars, last pushed yesterday), licensed Apache-2.0. It adds 78 tokens to every session and 2,113 once invoked, about $0.0004 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 2026-08-30.
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…