tool-operator

A guide for coordinating files, terminals, browsers, and connected applications while checking for human approval before risky actions. It covers actions such as deleting data, publishing content, accessing credentials, and changing system settings.

In plain words
What is it for?
Running local tasks, handling files and tools, reviewing uncertain actions, and recording limited operational outcomes without storing secrets.
Why use it?
It helps an agent choose safe, limited actions and prevents consequential changes from happening without immediate approval.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sdfdu/evopilot/tool-operator
Any agent
npx skills add sdfdu/evopilot --skill tool-operator
Clone the repo
git clone --depth 1 https://github.com/sdfdu/evopilot

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00183
Opus 5 $0.00013 $0.00092
Sonnet 5 $0.00005 $0.00037
Haiku 4.5 $0.00003 $0.00018

Measured 2d ago against content hash db5fb436de1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-operator 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.

plugins/evopilot/skills/tool-operator/SKILL.md · 21 lines

What it actually says

Tool Operator

Choose the narrowest tool that can complete the job and reuse established app-specific workflows when they remain relevant.

Autonomously perform local, recoverable work inside the authorized workspace. Before an action with unclear risk, call evopilot_review_action.

Human approval is required immediately before:

  • deleting material data or bulk overwriting files;
  • sending, posting, publishing, purchasing, or making resources public;
  • accessing credentials or logging into a new account;
  • changing system-wide configuration;
  • installing or enabling a new MCP server or expanding its permissions.

Do not treat approval for one action as standing authorization. Record tool category, outcome, and friction only; never persist raw credentials, private page content, or command output as behavioral memory.

Files

What ships with it

1 file 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.

Changes

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.

  1. 2d ago First seen · 21 lines · 26 tokens per session scan A db5fb436de1d

Subscribe to this mod's changes

tool-operator is a skill published in the GitHub repository sdfdu/evopilot (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 183 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.

Related

Other skills, from other repositories

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens

linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

jmagar/claude-homelab · 69 tokens

debugging-mutations

Verify what changed on a ServiceNow instance after a tool call — sysaudit inspection, syslog/transaction logs, session context, Flow Designer execution logs, outbound HTTP traces.

serac-labs/serac · 41 tokens

maya-shot-export

Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).

dcc-mcp/dcc-mcp-maya · 60 tokens