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/modeled-information-format/mnemonicWrote 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/modeled-information-format/mnemonic/setup)<a href="https://agentmods.dev/commands/modeled-information-format/mnemonic/setup"><img src="https://agentmods.dev/badge/commands/modeled-information-format/mnemonic/setup/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/modeled-information-format/mnemonic/setup"><img src="https://agentmods.dev/badge/commands/modeled-information-format/mnemonic/setup.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 | $0.00008 | $0.02311 |
| Opus 5.5 | $0.00003 | $0.00924 |
| Sonnet 5.5 | $0.00002 | $0.00462 |
| Haiku 4.5 | $0.00001 | $0.00231 |
Grade B, and why
setup scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
if ! grep -q "## Mnemonic Memory System" ~/.claude/CLAUDE.md 2>/dev/null; then How it starts
The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
/mnemonic:setup
Configure Claude to proactively use mnemonic memory without user intervention.
What This Command Does
- Prompts user for memory store path (default:
~/.claude/mnemonic) - Creates
~/.config/mnemonic/config.jsonwith user's choice - Detects organization from git remote
- Detects project name from git root
- Creates unified mnemonic directory structure under
${MNEMONIC_ROOT}/{org}/{project}/ - Initializes git repository for versioning
- Appends proactive behavior instructions to
~/.claude/CLAUDE.md(global only) - Creates initial project context memory
- If memories exist at old path and user chose different path, auto-migrates
Arguments
--force- Overwrite existing mnemonic configuration sections
Procedure
Step 0: Configure Memory Store Path
Ask the user where to store memories. Create the config file at the fixed XDG location.
# Check for existing config
if [ -f ~/.config/mnemonic/config.json ]; then
STORE_PATH=$(python3 -c "import json; print(json.load(open('$HOME/.config/mnemonic/config.json'))['memory_store_path'])")
echo "Existing config found. Memory store path: $STORE_PATH"
else
STORE_PATH="~/.claude/mnemonic"
fi
Ask the user: "Where should mnemonic store memories? (default: ~/.claude/mnemonic)"
After the user responds (or accepts default):
# Create config directory and file
mkdir -p ~/.config/mnemonic
cat > ~/.config/mnemonic/config.json << EOF
{
"version": "1.0",
"memory_store_path": "$STORE_PATH"
}
EOF
echo "Config saved to ~/.config/mnemonic/config.json"
# Expand for use in subsequent steps
STORE_PATH_EXPANDED="${STORE_PATH/#\~/$HOME}"
Step 1: Detect Context
# Organization from git remote
ORG=$(git remote get-url origin 2>/dev/null | sed -E 's|.*[:/]([^/]+)/[^/]+\.git$|\1|' | sed 's|\.git$||')
[ -z "$ORG" ] && ORG="default"
# Project from git root
PROJECT=$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null)
[ -z "$PROJECT" ] && PROJECT=$(basename "$PWD")
echo "Organization: $ORG"
echo "Project: $PROJECT"
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 Changed 91677f55e5c4
- 1mo ago First seen · 301 lines · 8 tokens per session scan B 1c7db8504108
setup is a command published in the GitHub repository modeled-information-format/mnemonic (23 stars, last pushed 3d ago), licensed MIT. It adds 8 tokens to every session and 2,311 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
dream-defrag
A command for pruning Claude Code’s saved memory files, including MEMORY.md and other memory notes.
context-preload
A command for managing and setting up ContextPreloader.
voice-refresh
Refresh the founder-voice DNA from new Granola meetings (interactive, MCP-backed). Pulls meetings since the last refresh, harvests Assaf-only speech, runs the Stage 2-3 orchestrator, and presents a founder-gated delta. Never auto-writes voice-dna.md.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
status
Show memex statistics and status including projects, memos, and pending items.
learn
Command "learn" from datacore-one/datacore, covering /learn, purpose, when to use, usage and quick capture.