Borrowing it
Nothing to install: this file belongs to solanabr/solana-vault-standard. 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/solanabr/solana-vault-standard/main/.claude/commands/diff-review.mdgit clone --depth 1 https://github.com/solanabr/solana-vault-standardWrote 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/commands/solanabr/solana-vault-standard/diff-review)<a href="https://agentmods.dev/commands/solanabr/solana-vault-standard/diff-review"><img src="https://agentmods.dev/badge/commands/solanabr/solana-vault-standard/diff-review.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.01943 |
| Opus 5 | $0.00006 | $0.00971 |
| Sonnet 5 | $0.00002 | $0.00389 |
| Haiku 4.5 | $0.00001 | $0.00194 |
Grade A, and why
diff-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to diff-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing the current branch diff for Solana-specific security issues, code quality problems, and anti-patterns. Output categorized findings with line references and fix suggestions.
Related Skills
- ext/solana-dev/skill/references/security.md - Vulnerability categories
- ext/trailofbits/plugins/building-secure-contracts/skills/solana-vulnerability-scanner/ - Automated scanning
Step 1: Get the Diff
# Determine base branch
BASE_BRANCH="main"
if ! git rev-parse --verify "$BASE_BRANCH" >/dev/null 2>&1; then
BASE_BRANCH="master"
fi
echo "Reviewing diff: $BASE_BRANCH...HEAD"
echo "Branch: $(git branch --show-current)"
echo ""
# Get the full diff
git diff "$BASE_BRANCH"...HEAD
echo ""
echo "Changed files:"
git diff --name-only "$BASE_BRANCH"...HEAD
echo ""
echo "Diff stats:"
git diff --stat "$BASE_BRANCH"...HEAD
Step 2: Check for Critical Issues
Scan the diff for each category. Report with file path, line number, and severity.
Account Validation
echo "=== Account Validation Check ==="
# Find Anchor account structs in changed files
CHANGED_RS=$(git diff --name-only "$BASE_BRANCH"...HEAD | grep '\.rs$')
if [ -n "$CHANGED_RS" ]; then
echo "Checking Rust files for account validation..."
# Missing owner checks in native programs
for f in $CHANGED_RS; do
[ -f "$f" ] || continue
grep -n "AccountInfo" "$f" | head -20
done
# Check for accounts missing constraints in Anchor
for f in $CHANGED_RS; do
[ -f "$f" ] || continue
# Accounts without any constraint attribute
grep -n "pub.*Account<" "$f" | grep -v "#\[account" | head -20
done
fi
Arithmetic Safety
echo ""
echo "=== Arithmetic Safety Check ==="
if [ -n "$CHANGED_RS" ]; then
for f in $CHANGED_RS; do
[ -f "$f" ] || continue
# Unchecked arithmetic operators on likely numeric operations
grep -n -E '\b\w+\s*[+\-\*]\s*\w+' "$f" | grep -v "checked_" | grep -v "//" | grep -v "test" | head -20
done
fi
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.
- 7d ago First seen · 248 lines · 12 tokens per session scan A 52af70f93344
diff-review is a command published in the GitHub repository solanabr/solana-vault-standard (23 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 1,943 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to diff-review, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
diff-review
AI-powered diff review for Solana-specific issues and code quality.
auditor:re-audit
Fix-review / re-audit. Takes a prior audit report + the current tree and classifies every prior finding FIXED / PARTIALLY-FIXED / STILL-OPEN / REGRESSED / ACKNOWLEDGED / DISPUTED (re-running Rule 5b on the fix, citing the remediation commit/PR hash), audits the changed surface for NEW findings via the diff-audit path…
auditor:audit-assist
Flow B — AI-assisted iterative audit with a human in the loop. Same lifecycle as audit-cycle, but pauses at checkpoints to surface confirmed findings, the next-focus plan, and targeted questions only the human can answer (business context, trust model, severity calls). The human steers; the agent re-synthesizes toward…
auditor:intake
Interactive engagement intake (alias /scope). Walks QUESTIONS.md and persists the answers to audit /intake.md — the durable intake artifact both audit-cycle and audit-assist read, instead of answers living only in conversation state. Captures scope + commit pin, languages/frameworks, protocol class, compliance…
auditor:diff-audit
PR / commit-scoped differential audit — audits only changed functions (plus 1-hop callers), flags removed security checks, and prioritizes by risk × blast radius.
auditor:economic-sim
Quantify a candidate economic finding — compute attack cost vs extractable value and, when possible, reproduce deposit→manipulate→withdraw against a Surfpool mainnet-fork for a real P/L figure.