Borrowing it
Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. 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/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-md-Coherent/SKILL.mdgit clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-DelphiWrote 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/gabrielondelphi/claude-tools-for-delphi/light-md-coherent)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-md-coherent"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-md-coherent/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/gabrielondelphi/claude-tools-for-delphi/light-md-coherent"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-md-coherent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 49 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00138 | $0.03610 |
| Opus 5 | $0.00069 | $0.01805 |
| Sonnet 5 | $0.00028 | $0.00722 |
| Haiku 4.5 | $0.00014 | $0.00361 |
Grade A, and why
light-md-Coherent 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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-md-Coherent — say it again, in plain words
The last answer was correct but hard to read: too long, too abstract, or full of words from someone else's field. This skill re-says it. It is a translation of the previous answer, not a second attempt at it.
If you catch yourself re-reading a file, re-running a tool, or re-thinking the problem — stop. That is not this skill.
This skill cannot stay switched on, and no wording inside this file can make it stay switched on. Claude Code loads the body of a SKILL.md only at the moment the skill runs; nothing re-reads it afterwards, so a line saying "remain active" would drift backwards with the rest of the text and stop having force. A standing voice lives in an output style instead — a file in c:\Users\<you>\.claude\output-styles\, switched on by "outputStyle" in c:\Users\<you>\.claude\settings.json. Its text goes into the system prompt and gets re-announced through the whole session, which is what makes it stick. If someone asks why this skill "does not stick", that is the answer: check whether an output style is set, and do not answer from memory.
This is a cheap operation. Do not spend deep reasoning on it. The thinking was already done in the message being rewritten; all that is left is choosing shorter words. No effort pin is set on purpose — a frontmatter pin binds only when the slash command is typed, and this skill is mostly reached through plain phrases like "say that simply". This line works on both paths.
Modes — picked by the argument
| Argument | Mode | Output |
|---|---|---|
| (none) | Plain | The same answer, plain words, short sentences. Same coverage, fewer syllables. |
a number, e.g. 3 |
Points | Exactly N numbered points, most important first. Nothing else — no intro, no closing. Never pad: if the target message holds fewer than N real points, give the ones that exist and say how many there were. |
a phrase or question, e.g. what is a DFM binding? or the part about the mutex — or a bare "I have no clue" that names no part |
Zoom | The missing fact first, in plain words, then that part again. Ignore the rest of the answer. When no part is named, you pick it: the one that needed knowledge the reader does not have. |
a file path, or this file |
File | Same rewrite, applied to that Markdown file (or the section named). Edit in place. |
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.
- 4d ago Changed · +17 lines · -2 tokens per session 5b0a7b8b9a9b
- 8d ago Changed · +2 lines 0b4f71420ff5
- 12d ago First seen · 101 lines · 140 tokens per session scan A 58e3f71678a5
light-md-Coherent is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (18 stars, last pushed 5d ago), licensed MPL-2.0. It adds 138 tokens to every session and 3,610 once invoked, about $0.0007 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…