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-review-Critical/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-review-critical)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-review-critical"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-critical/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-review-critical"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-review-critical.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 | $0.00112 | $0.01982 |
| Opus 5.5 | $0.00045 | $0.00793 |
| Sonnet 5.5 | $0.00022 | $0.00396 |
| Haiku 4.5 | $0.00011 | $0.00198 |
Grade A, and why
light-review-Critical 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 1mo 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/light-review-Critical — Delphi Post Review
Take the review findings already in this conversation and run them through a counter-analysis pass before fixing anything. Some of your suppositions WILL be false — this happens every review. Treat the prior findings as a hypothesis, not a verdict. This is a general skill, not necessarily only for Delphi code.
Precondition: if there are no review findings, list, or audit results in this conversation to work from, stop and tell the user: "No prior findings found in this session — there is nothing to counter-analyze." Do not invent findings to vet.
Step 0 — Say where the findings came from
Before arguing about anything, write one line per finding — or one line for the whole batch if they share an origin — naming who produced it:
- This same conversation, by you, earlier in this session.
- A sub-agent you launched from this session.
- An earlier, separate run that no longer exists — a report on disk, a file the user pasted in, another console's output.
This is not bookkeeping. It says how much the batch is worth before you spend an hour on it. A re-check inside the same session that produced the findings is the weakest of the four ways this has been measured: it caught 21.7% of planted errors against 28.6% for a brand new console reading the document cold, and it raised the wrong complaints from 3.1 to 4.4 per document (Song, arXiv:2603.12123).
So when the findings were produced in THIS conversation, say this to the user in one line, then carry on with the run:
"These findings were made earlier in this same session, which is the weakest window for checking them. A fresh console reading them cold does better. Say the word and I stop; otherwise I continue here."
Do not stall waiting for an answer — starting over costs him a paste and a new window, and that is his call to make, not a reason to leave the work sitting. If he does move it to a fresh console, nothing downstream breaks: the fixes get applied in that new console, and light-review-PostEdit at Step 5 verifies the edits of whichever session applied them.
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.
- 1mo ago Changed · +28 lines · +38 tokens per session 966fb7a0f808
- 1mo ago Changed · +2 lines 9d02cfa3c08e
- 2mo ago First seen · 85 lines · 74 tokens per session scan A 1aaed30afefd
light-review-Critical is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (23 stars, last pushed 28d ago), licensed MPL-2.0. It adds 112 tokens to every session and 1,982 once invoked, about $0.0004 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…