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 skills add argonautsystems/InvestorClaw --skill hermesgit 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/skills/argonautsystems/investorclaw/hermes)<a href="https://agentmods.dev/skills/argonautsystems/investorclaw/hermes"><img src="https://agentmods.dev/badge/skills/argonautsystems/investorclaw/hermes/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/skills/argonautsystems/investorclaw/hermes"><img src="https://agentmods.dev/badge/skills/argonautsystems/investorclaw/hermes.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 | $0.00045 | $0.02915 |
| Opus 5 | $0.00023 | $0.01458 |
| Sonnet 5 | $0.00009 | $0.00583 |
| Haiku 4.5 | $0.00005 | $0.00292 |
Grade A, and why
investorclaw 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 10d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InvestorClaw — Hermes Skill (v4.0)
Powered by InvestorClaw (Apache 2.0). This skill file is MIT-0-licensed; the underlying service is Apache 2.0.
TL;DR for hermes operators
InvestorClaw v4.0 turns hermes into a first-class portfolio-analysis
agent. The service runs as two local Docker containers and exposes
its capabilities over MCP-HTTP. Hermes 0.12+ registers the MCP servers
as native function-callable tool sources — the LLM sees
investorclaw.portfolio_ask, mnemos.search_memories, and friends in
the same tool catalog as browser_*, terminal, and skill_view.
Headline upgrade — HER-1 is gone. Read the next section if you remember v2.x.
What changed since v2.x — HER-1 elimination
If you ran InvestorClaw v2.x against hermes, you hit HER-1: the
"skill-as-doc-hint" caveat. In v2.x, InvestorClaw shipped as a hermes
skill bundle injected into the system prompt. The LLM had to use
hermes meta-tools (skill_view, terminal) to read the skill
documentation and then imitate the analyst commands by shelling out.
That indirection layer was lossy and slow, and the Linux baseline
empirical reliability landed around 8% (2.3/30) on the standard
prompt barrage — vs 77% on zeroclaw, which had real tool
registration.
v4.0 ends that. There is no skill bundle to inject. The
deterministic engine runs as a containerized service and publishes its
analytical surface over MCP-HTTP. Hermes 0.12+ registers MCP servers
declaratively in ~/.hermes/config.yaml and exposes their tools to
the LLM directly — same dispatch path as any other built-in tool.
What this means in practice for hermes users:
- No more meta-tool indirection. The LLM calls
investorclaw.portfolio_askdirectly, not viaskill_view→terminal→ fragile shell parsing. - Reliability now matches other agent runtimes. Expect the same routing accuracy as zeroclaw / openclaw — roughly an order of magnitude better than v2.x on the same prompts.
- Memory is built in. The
mnemos.*tool family gives hermes a persistent memory layer it never had before, scoped to InvestorClaw observations and user preferences. - No skill bundle to keep in sync. Bumping the service to a newer
ic-engine version is
docker compose pull && docker compose up -d. The tool catalog hermes sees is whatever the running service publishes.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 261 lines · 45 tokens per session scan A 29895ce7ff2a
investorclaw is a skill published in the GitHub repository argonautsystems/InvestorClaw (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,915 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 skills, from other repositories
fundraising-and-investor-relations
Raises capital and manages the relationship afterward — deciding how much and why, understanding what dilution and preferences actually cost, running a process with real competitive tension, preparing for diligence before it starts, and reporting to investors and a board in a way that keeps support when results are…
chief-financial-officer
Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls…
internal-controls-and-audit
Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…
sales-compensation-and-territory
Designs quotas, territories and commission plans that produce the behavior the business needs — sizing territories against real potential, setting quotas people can hit often enough to believe in, choosing what to pay on, handling accelerators, draws, clawbacks and disputes, and changing a plan without destroying…
capital-structure-and-covenants
Decides how the business is financed and what that financing then requires of it — debt versus equity, weighted average cost of capital as a hurdle rate, how much leverage cash flow can carry, and the financial, affirmative and negative covenants, definitions, test dates and cure rights that come attached. Use this to…
cost-accounting
Establishes what something actually costs — fixed, variable and mixed cost behavior, absorption versus variable costing, job-order, process and activity-based methods, breakeven and operating leverage, and price/volume/mix decomposition. Use this to set a price floor, explain why revenue or margin moved, decide make…