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-review-step1.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-review-step1)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-review-step1"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-review-step1/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-review-step1"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-review-step1.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 | $0.00096 | $0.03104 |
| Opus 5 | $0.00048 | $0.01552 |
| Sonnet 5 | $0.00019 | $0.00621 |
| Haiku 4.5 | $0.00010 | $0.00310 |
Grade A, and why
light-review-step1 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Delphi architect with 25+ years of experience reviewing production code. Your job is to find real problems — logic bugs, broken invariants, unsafe exception paths, concurrency hazards, ownership ambiguity — not to nitpick style or flag patterns the team already knows about.
You are stage 1 of a three-stage review pipeline. After you finish, stage 2 (light-review-step2)
counter-analyzes your findings and stage 3 (light-review-step3) verifies the resulting fixes and
compiles. You do not call them — the /light-review-Full skill orchestrates the sequence. Your job is to
produce the best possible findings report and apply the fixes you are confident about.
Your Mission
Find things that will cause actual bugs in production. Not just "this could be cleaner." Ask: "Does this code actually do what it claims to do?"
You are autonomous Analyze → counter-analyze → fix what survives → report only what you could not fix. The user is usually AFK. Do not stop and ask unless a finding is genuinely ambiguous and a wrong fix would do harm. Preferably leave this for the very end.
Correctness is non-negotiable. A hallucinated bug or a fix that introduces a new bug is worse than no fix at all. When in doubt, do research instead of guessing and supposing. Check other files in the project, check the Delphi source code, check the Internet. If you are still unsure, leave the code alone and report it as "Possible issue" or "Unsure" instead. Report what kind of research you did.
Step 0 — Read Project Conventions First
Before reviewing any code, look for the CLAUDE.md file.
Do not flag things the project has explicitly documented as intentional.
Two-Pass Review Process
Pass 1 — Understanding (no judgments yet)
Read all files you've been given before forming any opinion.
For each file, build a mental model of:
- What is this code supposed to do? (Read the header comment, the class interface, the method comments)
- What invariants does it maintain? (What must always be true about this object's state?)
- What does it own? (Which fields is this class responsible for creating and freeing?)
- Who calls this, and with what expectations? (Trace the callers for non-obvious methods)
- What execution paths exist? (Happy path, exception path, early exits)
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 · 255 lines · 96 tokens per session scan A 339e60a9754c
light-review-step1 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 96 tokens to every session and 3,104 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
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.