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.
npx agentmods add commands/ukkit/memcord/toon-decodegit clone --depth 1 https://github.com/ukkit/memcordWhat 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 | $0.00000 | $0.01354 |
| Opus 5 | $0.00000 | $0.00677 |
| Sonnet 5 | $0.00000 | $0.00271 |
| Haiku 4.5 | $0.00000 | $0.00135 |
Grade A, and why
toon-decode 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 yesterday.
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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TOON Decode
Convert TOON v2.0 format back to JSON using the Zig decoder.
Usage: /toon-decode <file> [options]
Options:
--strict- Enable strict mode validation during decoding--no-expand-paths- Don't expand folded paths (keep dot notation)
Execute the following workflow:
1. Validate Input
FILE="$1"
if [[ -z "$FILE" ]]; then
echo "Usage: /toon-decode <file> [options]"
echo "Example: /toon-decode data.toon"
echo "Example: /toon-decode data.toon --strict"
exit 1
fi
if [[ ! -f "$FILE" ]]; then
echo "❌ Error: File not found: $FILE"
exit 1
fi
if [[ ! "$FILE" =~ \.toon$ ]]; then
echo "⚠️ Warning: File doesn't have .toon extension"
read -p "Continue? (y/n) " -n 1 -r
echo
if [[ ! $REPLY =~ ^[Yy]$ ]]; then
exit 0
fi
fi
echo "✓ Input: $FILE"
2. Parse Options
STRICT_FLAG=""
EXPAND_PATHS_FLAG=""
OUTPUT="${FILE%.toon}.json"
shift # Remove first arg (filename)
while [[ $# -gt 0 ]]; do
case "$1" in
--strict)
STRICT_FLAG="--strict"
shift
;;
--no-expand-paths)
EXPAND_PATHS_FLAG="--no-expand-paths"
shift
;;
*)
shift
;;
esac
done
echo "⚙️ Configuration:"
echo " Strict mode: ${STRICT_FLAG:-disabled}"
echo " Path expansion: ${EXPAND_PATHS_FLAG:-enabled (default)}"
echo " Output: $OUTPUT"
3. Check Zig Binary
TOON_BIN=".claude/utils/toon/zig-out/bin/toon"
if [[ ! -f "$TOON_BIN" ]]; then
echo "❌ Zig binary not found. Building..."
echo ""
cd .claude/utils/toon
/opt/homebrew/opt/[email protected]/bin/zig build -Doptimize=ReleaseFast
cd -
echo ""
echo "✓ Build complete"
fi
4. Decode
echo ""
echo "Decoding..."
$TOON_BIN decode "$FILE" \
$STRICT_FLAG \
$EXPAND_PATHS_FLAG \
> "$OUTPUT"
if [[ $? -eq 0 ]]; then
echo "✓ Decoding successful"
else
echo "❌ Decoding failed"
exit 1
fi
5. Validate JSON
# Verify JSON is valid
if command -v python3 &> /dev/null; then
python3 -m json.tool "$OUTPUT" > /dev/null 2>&1
if [[ $? -eq 0 ]]; then
echo "✓ JSON validation passed"
else
echo "⚠️ Warning: Output may not be valid JSON"
fi
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.
- yesterday First seen · 240 lines · 0 tokens per session scan A 53cc21f403a8
toon-decode is a command published in the GitHub repository ukkit/memcord (72 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,354 tokens. 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
compress
Save this Claude Code session to the vault and update the semantic memory index.
checkpoint
Save a mid-session checkpoint — for continuity between sessions of the same day.
resume
Load context from the vault before starting work.
preserve
Scan this conversation and silently save anything worth permanent memory.
update-model
Change an OpenClaw model configuration — with mandatory discovery, provider-aware validation, and 5-step verification. Designed to prevent every class of model configuration error.
fleet-announce
Announce a fleet update to users — send a personalized message from each person's bot explaining what changed and why they should care.