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/integrategit 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 | $0.00012 | $0.01287 |
| Opus 5 | $0.00006 | $0.00643 |
| Sonnet 5 | $0.00002 | $0.00257 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade A, and why
integrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mnemonic:integrate
Integrate mnemonic memory capture and recall into another Claude Code plugin.
Arguments
<plugin_path>- Required. Path to target plugin directory--analyze- Show proposed changes without applying--dry-run- Show detailed diff of what would change--remove- Remove mnemonic protocol (delete content between sentinel markers)--migrate- Convert old marker-less integrations to marker-wrapped format--verify- Verify integration integrity matches template--rollback- Revert the last mnemonic integration commit
Procedure
Step 1: Call Python Implementation
The integration is handled by the Python library in skills/integrate/lib/.
PLUGIN_PATH="${1:?Error: Plugin path required}"
PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(dirname $(dirname $0))}"
# Parse mode from arguments
MODE="integrate"
DRY_RUN=""
for arg in "$@"; do
case "$arg" in
--analyze|--dry-run) DRY_RUN="--dry-run" ;;
--remove) MODE="remove" ;;
--migrate) MODE="migrate" ;;
--verify) MODE="verify" ;;
--rollback) MODE="rollback" ;;
esac
done
# Validate plugin path
if [ ! -f "${PLUGIN_PATH}/.claude-plugin/plugin.json" ]; then
echo "Error: Not a valid plugin directory (missing .claude-plugin/plugin.json)"
exit 1
fi
# Handle rollback separately
if [ "$MODE" = "rollback" ]; then
cd "${PLUGIN_PATH}"
if [ ! -d .git ]; then
echo "Error: No git repository for rollback"
exit 1
fi
# Find the mnemonic integration commit (not just any commit)
COMMIT=$(git log --oneline --grep="feat(mnemonic)" --grep="chore(mnemonic)" -1 | cut -d' ' -f1)
if [ -z "$COMMIT" ]; then
echo "Error: No mnemonic integration commit found"
echo "Looking for commits with 'feat(mnemonic)' or 'chore(mnemonic)' in message"
exit 1
fi
echo "Found mnemonic integration commit: $COMMIT"
git show --stat "$COMMIT"
echo ""
echo "Reverting this commit..."
git revert "$COMMIT" --no-edit
echo "Rollback complete: $(git log -1 --oneline)"
exit 0
fi
# Run Python integrator
python3 "$PLUGIN_DIR/skills/integrate/lib/integrator.py" \
"${PLUGIN_PATH}" \
--mode "$MODE" \
$DRY_RUN \
--git-commit
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.
- 2d ago First seen · 181 lines · 12 tokens per session scan A 696bfdd72acd
integrate is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,287 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
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.
prd-triage
Triage pending findings on the active PRD.
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.