agent-canvas-environment

A guide for working inside a local Agent Canvas setup, where a local web interface and backend let agents inspect projects and delegate tasks.

In plain words
What is it for?
Use it to find the local Agent Canvas services, authenticate safely, inspect repositories, and delegate work through the local backend.
Why use it?
It reduces setup mistakes around local services, authentication, ports, workspace safety, and sending complete instructions to another conversation.

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/openhands/extensions/agent-canvas-environment
Any agent
npx skills add OpenHands/extensions --skill agent-canvas-environment
Clone the repo
git clone --depth 1 https://github.com/OpenHands/extensions

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00046 $0.02530
Opus 5 $0.00023 $0.01265
Sonnet 5 $0.00009 $0.00506
Haiku 4.5 $0.00005 $0.00253

Measured 2d ago against content hash 40562401fb3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-canvas-environment scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -o /tmp/agent-canvas-conversations.json -w '%{http_code}\n' \
skills/agent-canvas-environment/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Canvas Environment

Use this skill when running inside or alongside a local Agent Canvas stack, especially when the user asks to inspect the local backend, create or monitor local conversations, or delegate work to another local conversation.

Core rules

  • Treat the local Agent Canvas backend as an agent-server API, usually http://localhost:8001.
  • Treat the local UI as a separate frontend, usually http://localhost:8000.
  • Do not print session API keys. Pass them directly in X-Session-API-Key.
  • Trust any runtime-services block or explicit user-provided host over default ports.
  • Before mutating a repository, check git status -sb. If a worktree has unrelated changes, use a separate worktree or clone.
  • When delegating, write a self-contained prompt. The new conversation does not inherit the current chat context.

Find the session key

Use the first available value, without echoing it:

KEY="${SESSION_API_KEY:-${OH_SESSION_API_KEYS_0:-${LOCAL_BACKEND_API_KEY:-}}}"
if [ -z "$KEY" ] && [ -f "$HOME/.openhands/agent-canvas/api-key.txt" ]; then
  KEY="$(tr -d '\n' < "$HOME/.openhands/agent-canvas/api-key.txt")"
fi
test -n "$KEY" || { echo "No Agent Canvas session API key found" >&2; exit 1; }

Validate backend access:

curl -sS -o /tmp/agent-canvas-conversations.json -w '%{http_code}\n' \
  -H "X-Session-API-Key: $KEY" \
  http://localhost:8001/api/conversations/search

HTTP 200 means the backend and key work.

Delegate to a local conversation

Use POST /api/conversations with:

  • the encrypted agent_settings from GET /api/settings (with X-Expose-Secrets: encrypted), which carries the real Fernet-encrypted llm.api_key, the existing agent_context, and the agent kind — so you never handle plaintext credentials and you don't drop the caller's skill/context config
  • secrets_encrypted: true so the agent-server decrypts that api_key server-side
  • the exec tool set merged into agent_settings.tools (and task_tool_set when you enable sub-agents)
  • tool_module_qualnames for any non-SDK tools (e.g. canvas_ui)
  • agent_context.load_public_skills/load_user_skills/load_project_skills set to true if the delegated agent should inherit bundled/user/project skills
  • a fresh absolute workspace directory
  • initial_message.run: true
  • worktree: false when the workspace is already isolated

Read the full file on GitHub · 203 lines

Files

What ships with it

4 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.

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 · 203 lines · 46 tokens per session scan A 40562401fb3e

Subscribe to this mod's changes

agent-canvas-environment is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 46 tokens to every session and 2,530 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens