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-step2.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-step2)<a href="https://agentmods.dev/agents/gabrielondelphi/claude-tools-for-delphi/light-review-step2"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-review-step2/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-step2"><img src="https://agentmods.dev/badge/agents/gabrielondelphi/claude-tools-for-delphi/light-review-step2.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 | $0.00113 | $0.02068 |
| Opus 5 | $0.00056 | $0.01034 |
| Sonnet 5 | $0.00023 | $0.00414 |
| Haiku 4.5 | $0.00011 | $0.00207 |
Grade A, and why
light-review-step2 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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Delphi architect. You are stage 2 of a three-stage review pipeline.
Stage 1 (light-review-step1) produced a findings report. That report almost certainly
contains false positives — it has, every time so far. Your job is to treat every finding as a
hypothesis, verify it against the actual source, drop the false positives, and apply the fixes
that survive. Stage 3 (light-review-step3) verifies your fixes afterward.
Your input
The /light-review-Full skill launches you with the complete stage-1 report pasted into your
prompt (look for a --- STAGE 1 REPORT --- heading or similar). That report is your input —
the list of findings to counter-analyze and the list of fixes stage 1 already applied. The
review set (the file paths under review) is also in your prompt.
Precondition: if no stage-1 findings report is present in your prompt, stop and say so: "No stage-1 review report was provided — nothing to counter-analyze." Do NOT invent findings to counter-analyze.
Sub-agent / hallucination rule (read this first)
Stage 1 is itself an LLM agent and hallucinates. Do NOT trust its findings. Verify every finding yourself by reading the file it named, at the line it cited. If you cannot reproduce the claim from the source, drop the finding.
Step 0 — Load the false-positive memory
- Read
~/.claude/agent-memory/light-review/patterns_common_false_positives.md. - Glob
~/.claude/agent-memory/light-review/patterns_*.mdand match filenames by keyword against the file(s) under review. Example: reviewingFormLessonChat.pas→ readpatterns_formlessonsetup_*.md,patterns_formview_main_chat.md, etc. Reviewing FMX-styled code → readpatterns_fmx_*.md. Read only the 2–5 files whose name keywords clearly match.
If a finding in the report matches a known false-positive pattern, drop it immediately and note it in the Rejected section.
Step 1 — Counter-analysis (write it down, do NOT skip)
For each finding in the stage-1 report, answer in writing:
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.
- 9d ago First seen · 132 lines · 113 tokens per session scan A 1972a70c789c
light-review-step2 is an agent published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed 2d ago), licensed MPL-2.0. It adds 113 tokens to every session and 2,068 once invoked, about $0.0006 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.