Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add KumihoIO/kumiho-plugins/plugin install kumiho-memoryWrote 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/kumihoio/kumiho-plugins/kumiho-onboard)<a href="https://agentmods.dev/commands/kumihoio/kumiho-plugins/kumiho-onboard"><img src="https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/kumiho-onboard/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/kumihoio/kumiho-plugins/kumiho-onboard"><img src="https://agentmods.dev/badge/commands/kumihoio/kumiho-plugins/kumiho-onboard.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 | $0.00021 | $0.03230 |
| Opus 5 | $0.00010 | $0.01615 |
| Sonnet 5 | $0.00004 | $0.00646 |
| Haiku 4.5 | $0.00002 | $0.00323 |
Grade A, and why
kumiho-onboard 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 6d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kumiho Onboarding Wizard
Run the onboarding wizard that configures the kumiho-memory plugin end-to-end: Python venv, backend selection, MCP server config, and skill ingestion into the graph.
Before any step: resolve the interpreter
No single interpreter name exists on every platform. Resolve by OS first.
On Windows, never execute python, python3, or a PATH-resolved py as a
probe: App Execution Aliases and shims can open Store/legacy application
windows. Derive the home directory from the OS account record, then use the
existing ~/.kumiho/venv/Scripts/python.exe; if it is absent, use only a
PE-validated Python Launcher at its OS-managed path. If neither works, stop and
report Python 3.10+ missing.
On macOS/Linux, derive the home directory from the OS account database, prefer
the shared ~/.kumiho/venv/bin/python, then probe only fixed absolute Python
locations. Never trust host/project HOME, PATH, or a shell shim.
The MCP server itself starts through the persistent
${CLAUDE_PLUGIN_DATA}/venv compatibility alias. The wizard also records a
known-good absolute KUMIHO_PYTHON for older external integrations. Resolve
the bootstrap interpreter here, in this shell:
KUMIHO_UID=$(/usr/bin/id -u) || exit 1
KUMIHO_ACCOUNT_HOME=""
KUMIHO_PASSWD=""
if [ -x /usr/bin/getent ]; then
KUMIHO_PASSWD=$(/usr/bin/getent passwd "$KUMIHO_UID")
elif [ -x /bin/getent ]; then
KUMIHO_PASSWD=$(/bin/getent passwd "$KUMIHO_UID")
fi
if [ -n "$KUMIHO_PASSWD" ]; then
IFS=: read -r _ _ _ _ _ KUMIHO_ACCOUNT_HOME _ <<EOF
$KUMIHO_PASSWD
EOF
elif [ -x /usr/bin/dscacheutil ]; then
KUMIHO_DS=$(/usr/bin/dscacheutil -q user -a uid "$KUMIHO_UID")
while IFS= read -r KUMIHO_LINE; do
case "$KUMIHO_LINE" in
"dir: "*) KUMIHO_ACCOUNT_HOME=${KUMIHO_LINE#dir: } ;;
esac
done <<EOF
$KUMIHO_DS
EOF
fi
case "$KUMIHO_ACCOUNT_HOME" in
/*) ;;
*) echo "Kumiho: OS account home could not be resolved safely" >&2; exit 1 ;;
esac
KUMIHO_SHARED_ROOT="$KUMIHO_ACCOUNT_HOME/.kumiho/venv"
KUMIHO_PY="$KUMIHO_SHARED_ROOT/bin/python"
if ! { [ -x "$KUMIHO_PY" ] && [ -f "$KUMIHO_SHARED_ROOT/pyvenv.cfg" ] &&
"$KUMIHO_PY" -I -S -c 'import sys; raise SystemExit(0 if sys.version_info >= (3,10) else 3)' 2>/dev/null &&
"$KUMIHO_PY" -I -c 'import os,sys; raise SystemExit(0 if os.path.realpath(sys.prefix) == os.path.realpath(sys.argv[1]) else 3)' "$KUMIHO_SHARED_ROOT" 2>/dev/null; }; then
KUMIHO_PY=""
for KUMIHO_CANDIDATE in /usr/bin/python3 /usr/local/bin/python3 /opt/homebrew/bin/python3; do
if [ -x "$KUMIHO_CANDIDATE" ] &&
"$KUMIHO_CANDIDATE" -I -S -c 'import sys; raise SystemExit(0 if sys.version_info >= (3,10) else 3)' 2>/dev/null; then
KUMIHO_PY="$KUMIHO_CANDIDATE"
break
fi
done
fi
[ -n "$KUMIHO_PY" ] || { echo "Kumiho: Python 3.10+ not found" >&2; exit 1; }
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.
- 6d ago Changed · +140 lines · +2 tokens per session scan B → A 51a9e6aa1825
- 11d ago First seen · 109 lines · 19 tokens per session scan B f0edb5327b92
kumiho-onboard is a command published in the GitHub repository KumihoIO/kumiho-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 3,230 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.