Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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-ai-kit/profile-cu)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/profile-cu"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/profile-cu/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/commands/solanabr/solana-ai-kit/profile-cu"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/profile-cu.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 | $0.00011 | $0.01273 |
| Opus 5 | $0.00005 | $0.00636 |
| Sonnet 5 | $0.00002 | $0.00255 |
| Haiku 4.5 | $0.00001 | $0.00127 |
Grade A, and why
profile-cu 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- profile-cu — 100% identical, 0 lines differ
- profile-cu — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are profiling CU (compute unit) consumption for a Solana program. This identifies expensive instructions and optimization opportunities.
Related Skills
- ext/solana-dev/skill/references/programs/pinocchio.md - CU optimization patterns
- ext/solana-dev/skill/references/testing.md - Test framework CU measurement
Step 1: Verify Program
echo "Detecting program..."
if [ ! -f "Anchor.toml" ]; then
echo "No Anchor.toml found. This command requires an Anchor project."
echo "For native programs, use 'solana program show <PROGRAM_ID>' and manual CU logging."
exit 1
fi
# Extract program IDs from Anchor.toml
echo "Programs in Anchor.toml:"
grep -A 5 '\[programs' Anchor.toml
# Check if deployed (optional)
CLUSTER=$(grep -m1 'cluster' Anchor.toml | sed 's/.*= *//' | tr -d '"')
echo "Cluster: ${CLUSTER:-localnet}"
Step 2: Build Program
echo "Building program..."
anchor build
if [ $? -ne 0 ]; then
echo "Build failed. Fix compilation errors before profiling."
exit 1
fi
# Report binary size
echo ""
echo "Program binary sizes:"
ls -lh target/deploy/*.so | awk '{print $5, $9}'
Step 3: Run Tests with CU Logging
echo "Running tests with CU profiling enabled..."
# Set environment for verbose CU logging
export SBF_OUT_DIR=target/deploy
export RUST_LOG=solana_runtime::message_processor=trace
# Run Anchor tests and capture output
anchor test --skip-deploy 2>&1 | tee /tmp/cu-profile-output.txt
TEST_STATUS=$?
if [ $TEST_STATUS -ne 0 ]; then
echo "Tests failed. Fix test failures before profiling CU."
exit 1
fi
Step 4: Parse CU Usage
Extract CU consumption from test output. Look for patterns like:
consumed X of Y compute unitsProgram <ID> consumed <N> of <M> compute units
echo ""
echo "=== CU Profile Results ==="
echo ""
# Extract CU lines from test output
grep -i "consumed.*compute units" /tmp/cu-profile-output.txt | \
sed 's/.*Program //' | \
sort -t' ' -k3 -n -r | \
head -50
echo ""
echo "--- Per-Instruction Breakdown ---"
echo ""
# Parse into table format
grep -i "consumed.*compute units" /tmp/cu-profile-output.txt | \
awk '{
for(i=1;i<=NF;i++) {
if($i=="consumed") { cu=$(i+1) }
if($i=="of") { limit=$(i+1) }
}
if(cu && limit) {
pct = (cu/limit)*100
printf "%-60s %8s / %-8s (%5.1f%%)\n", $0, cu, limit, pct
}
}'
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 · 160 lines · 11 tokens per session scan A 16254b82e53c
profile-cu is a command published in the GitHub repository solanabr/solana-ai-kit (101 stars, last pushed 19d ago), licensed MIT. It adds 11 tokens to every session and 1,273 once invoked, about $0.0001 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 commands, from other repositories
apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
explain-architecture
Analyze and explain software architecture with ASCII diagrams and pattern detection. Creates visual representations of system design.
prompt
Create or optimize prompts using best practices.
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
watch
Check for Claude Code updates, detect breaking changes, analyze plugin compatibility, and optionally gather community pulse via Exa.
db-migrate
You are a database migration expert specializing in zero-downtime deployments, data integrity, and multi-database environments. Create comprehensive migration scripts with rollback strategies, validation checks, and performance optimization.