AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Agent Config

skill-alfredxw-denova-agent-config · by alfredxw

Use when config_manager creates or updates Denova Agent page settings through agent config tools.

↗ Repository
— No reviews yet
0 installs
39 views
0.0% view→install

Install

$ agentstack add skill-alfredxw-denova-agent-config

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-alfredxw-denova-agent-config)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Agent Config? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Agent Config

Use this skill before calling write_agent_configs.

Workflow

  1. Call list_agent_configs first. It returns user, workspace, and effective Agent page settings in one response.
  2. Use write_agent_configs only for Agent page settings. Do not edit config.toml files directly.
  3. Always set scope explicitly to user or workspace. Use the scope requested by the user or shown by the current Agents page context.
  4. Preserve fields not requested by the user. For updates, copy the existing override from list_agent_configs, change only the requested fields, then send the complete replacement override.
  5. Delete or disable SubAgents only after the user clearly asked for it.

Supported Operations

  • set_agent_override: replace one Agent override in the selected layer.
  • agent: default, ide, interactive_story, config_manager, interactive_state, interactive_hot_choices, version_summary, tool_agent, automation, or context_compaction.
  • Optional replacement sections: model, tools, prompt, skills, context.
  • set_general_sub_agent: set or inherit the built-in General SubAgent switch.
  • agent: default, ide, interactive_story, config_manager, or automation.
  • enabled: true or false; omit/null to inherit.
  • upsert_sub_agent: create or replace one custom SubAgent in the selected layer.
  • Provide a complete sub_agent with id, description, and system_prompt.
  • Use enabled: false with the same id to shadow an inherited SubAgent.
  • delete_sub_agent: remove one custom SubAgent from the selected layer only.
  • This does not delete SubAgents inherited from another layer.

Field Notes

  • agent_config_read and agent_config_write are only meaningful for the Config Manager Agent and its configured SubAgents.
  • A SubAgent cannot gain tools disabled on its parent Agent. Tool settings are upper bounds, not grants beyond the parent.
  • model.profile_id must reference an existing model profile or be empty to inherit. This skill does not create model profiles.
  • prompt.flow_prompt changes Denova flow rules for an Agent. prompt.system_prompt adds user custom rules. Neither can override runtime contracts, output protocols, tool permissions, or backend validation.
  • Context compaction fields are ratios, not percentages: use 0.9 for 90%.

Safe Defaults

  • Use workspace scope for book-specific Agent behavior and user scope for personal defaults across books.
  • Prefer disabling one tool or one Skill over rewriting a full Agent prompt when the user asks for a capability boundary.
  • Prefer a focused custom SubAgent with narrow tools over broad changes to the parent Agent.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills