CC simmer-mcp-setup
One-shot bootstrap for the Simmer MCP server. Detects your agent runtime (Claude Code / Cursor / OpenClaw / Hermes / Codex / Grok Bot), installs simmer-mcp via npm, writes the right MCP config, prompts a restart, and verifies the tool handshake. Use after registering an agent on simmer.markets to run pre-built Simmer trading strategies through your MCP-aware agent.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
-
high Concealment
en-hide-from-userSKILL.md:630Instruction to hide actions from the user- **Don't tell the user "it should work now" without verifying.** Run Step 6 — confirm a real tool call returns real data.
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:82Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)If `command not found`, the user needs to install Node.js. **Don't auto-install via `curl | sh`** — it modifies the user's system without their approval. Instead, show them the platform-specific optio
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:627Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- **Don't auto-install Node.js via `curl | sh`** — modifying the user's system without explicit approval is bad practice. Show the platform-specific install hint and let the user decide.
quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9335 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "published"
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 9335 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 100Steps. 34 steps
- 100Failures and branches. 14 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (4 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 367: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (22 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.