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/argonautsystems/investorclaw/askgit clone --depth 1 https://github.com/argonautsystems/InvestorClawWrote 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/argonautsystems/investorclaw/ask)<a href="https://agentmods.dev/commands/argonautsystems/investorclaw/ask"><img src="https://agentmods.dev/badge/commands/argonautsystems/investorclaw/ask.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00578 |
| Opus 5 | $0.00018 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
ask scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the InvestorClaw natural-language entry point against the prebuilt
ic-engine container (no uv, no source clone). On first use this pulls the
public image; subsequent calls reuse it. Provider keys are read from the mounted
keys.env and are never baked into the image.
Execute:
IC_HOME="${IC_HOME:-$HOME/.investorclaw}"
IC_IMAGE="${IC_ENGINE_IMAGE:-ghcr.io/argonautsystems/ic-engine:4.7.7-cpu}"
mkdir -p "$IC_HOME/data/portfolios" "$IC_HOME/data/reports"
[ -f "$IC_HOME/data/keys.env" ] || touch "$IC_HOME/data/keys.env"
if ! docker image inspect "$IC_IMAGE" >/dev/null 2>&1; then
echo "📦 First run — pulling $IC_IMAGE (public, no auth, no build)..."
docker pull "$IC_IMAGE" || {
echo "❌ Could not pull the ic-engine image. Is Docker running? See docs/GETTING_STARTED.md."
exit 1
}
fi
docker run --rm \
--env-file "$IC_HOME/data/keys.env" \
-e INVESTORCLAW_PORTFOLIO_DIR=/data/portfolios \
-e IC_PORTFOLIO_DIR=/data/portfolios \
-v "$IC_HOME/data:/data" \
--entrypoint /opt/ic-engine/.venv/bin/investorclaw \
"$IC_IMAGE" ask "$ARGUMENTS"
Presentation:
- Present the engine narrator's answer clearly.
- Preserve all quoted source text, numerical values, timestamps, and freshness labels.
- Never fabricate portfolio, market, ticker, bond, news, or optimization data.
- If the first prompt takes 30–60 seconds, note that InvestorClaw is building the deterministic signed envelope; follow-up prompts should be cache-amortized.
Errors:
- If data looks stale, suggest
/investorclaw:refresh. - If setup or source data is missing, report the engine's exact guidance and point to
docs/GETTING_STARTED.md(drop a portfolio CSV into~/.investorclaw/data/portfolios/). - To set a provider key:
echo 'MASSIVE_API_KEY=<key>' >> ~/.investorclaw/data/keys.env(or any provider's key var — seedocs/PROVIDERS.md).
See ../DISCLAIMER.md
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.
- 5d ago First seen · 48 lines · 37 tokens per session scan A f4236797e2c6
ask is a command published in the GitHub repository argonautsystems/InvestorClaw (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 578 once invoked, about $0.0002 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
burn-rate
Compute the recent 7-day spend trend (burn rate) from daily sessions and per-session cost.
unit-economics
Unit economics analysis — CAC/LTV estimation, churn inference, gross margin per unit.
competitive
Competitive landscape analysis — peer positioning, market-share dynamics, moat assessment.
secular-trends
Secular technology trends analysis — technology adoption cycles, disruption risk, strategic positioning.
sector-overview
Sector overview — TAM estimation, competitive concentration (HHI), regulatory landscape.
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.