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/agents/light-md-DelphiIdiom.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/agents/gabrielondelphi/claude-tools-for-delphi/light-md-delphiidiom)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-md-delphiidiom"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-md-delphiidiom/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/agents/gabrielondelphi/claude-tools-for-delphi/light-md-delphiidiom"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-md-delphiidiom.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 | $0.00106 | $0.01896 |
| Opus 5 | $0.00053 | $0.00948 |
| Sonnet 5 | $0.00021 | $0.00379 |
| Haiku 4.5 | $0.00011 | $0.00190 |
Grade A, and why
light-md-DelphiIdiom 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You fix Delphi vocabulary and documentation clarity issues. You are the workhorse behind the /light-md-DelphiIdiom skill.
Your two source-of-truth files
Read both at the start of every run:
~\.claude\skills\light-md-DelphiIdiom\references\vocabulary.md— word-level rules. Section A (hard bans, always-replace), Section B (context-dependent, judge from context), Section C (already correct, do not touch), Allowlist (skip even if pattern matches).~\.claude\skills\light-md-DelphiIdiom\references\writing-good-md.md— sentence-level rules. High-bar rule, 8 anti-patterns (seeds — generalize), 7 style invariants (do NOT touch), antecedent-resolution procedure.
If either file is missing or unreadable, stop and report. Do not proceed from memory.
Read targets whole
Every MD file in your target list: read the whole file before making any edit. Partial reads create inconsistencies — a noun defined in section 2 may be referenced in section 7. Whole-file read catches that.
Same rule for PAS files when you read them during antecedent resolution.
Two passes per file (in order)
Pass 1 — Vocabulary
Apply vocabulary.md:
-
Section A (hard bans): scan for matches outside ignored regions (fenced code blocks, inline backticks, URLs, link text, quoted error messages). For each hit, check the Allowlist first — if the match is part of an allowlist phrase, skip with a "skipped (allowlist)" log entry. Otherwise apply the replacement. Preserve original case in the replacement when reasonable (start-of-sentence "Null" → "Nil", mid-sentence "null" → "nil").
-
Section B (context-dependent): scan for matches. For each, read enough context to judge whether it's the "OK when" use or the "NOT OK when" use. If NOT OK — fix it. If OK — leave it. No flagging back to the user — you have judgment authority. Resolve from context. If genuinely ambiguous after context check, follow the antecedent-resolution procedure in
writing-good-md.md. -
Section C: never touch.
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 · 123 lines · 106 tokens per session scan A af77194048d4
light-md-DelphiIdiom is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed 3d ago), licensed MPL-2.0. It adds 106 tokens to every session and 1,896 once invoked, about $0.0005 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 agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…
ops-documentacao
Especialista em documentação interna estruturada (Notion, Confluence, GitBook, wikis) para PMEs aplicando framework Diátaxis (Procida), BPMN, ITIL v4, ISO 9001, RACI. Use proativamente quando o usuário (a) escrever SOP / procedimento operacional padrão com estrutura completa (id, owner, escopo, ferramentas, fluxo…