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/modeled-information-format/mnemonic/setupgit clone --depth 1 https://github.com/modeled-information-format/mnemonicWhat 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 | $0.00008 | $0.02310 |
| Opus 5 | $0.00004 | $0.01155 |
| Sonnet 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 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.
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.
- yesterday First seen · 301 lines · 8 tokens per session scan B 1c7db8504108
setup is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 2,310 once invoked, about $0.0000 per session on Opus 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
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
wiring-check
End-of-task wiring gate — verify every change is connected end-to-end across kipi plugins, hooks, MCP tools, agents, bus files, canonical, and rules. Nothing dangling.
issue-closeout
Triage Codex findings via per-finding dispositions, record findingstriaged, close the active issue.
prd-personas
Run the Skeptic persona session against the active draft PRD.
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.