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 agentmods add skills/burakgon/roamcode/clinpx skills add burakgon/roamcode --skill cligit clone --depth 1 https://github.com/burakgon/roamcodeWhat 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 | $0.00021 | $0.00426 |
| Opus 5 | $0.00010 | $0.00213 |
| Sonnet 5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
roamcode-command-center 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 yesterday.
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.
What it actually says
RoamCode command center
Use the installed roamcode api wrapper. Set ROAMCODE_API_URL to the Node origin and provide a revocable device or
host credential in ROAMCODE_API_TOKEN. Never put a credential in a URL, command argument, log, or response.
Start by running roamcode api capabilities. The supported read actions are sessions, agents, workspaces,
devices, presence, adapters, events, and openapi.
presence contains only short-lived viewing metadata and never terminal content, prompts, credentials, IP addresses,
or private filesystem paths. Manual starts open a neutral shell and never choose a provider. Start Claude Code, Codex,
or another terminal command explicitly after the Session exists.
Mutations:
roamcode api start --cwd /absolute/projectopens a neutral persistent shell.roamcode api send --session SESSION_ID --data 'text'writes to that terminal.roamcode api wait --agent AGENT_ID --after UPDATED_AT --timeout-ms 30000roamcode api focus --agent AGENT_IDemits a non-stealing request. Add--activateonly when the user explicitly asked to switch their visible context.
Pass --idempotency-key when retrying a mutation across processes. A key is actor-scoped for 24 hours; reusing it
with another request returns IDEMPOTENCY_CONFLICT. send writes only to the Session's native terminal and returns
focused:false. Use wait or the resumable event stream instead of tight polling.
Treat blocked as requiring a decision, working as in progress, done as completed but unseen, and ended as no
longer running. Do not infer success from a transport timeout: read the resource again using the same idempotency key.
What ships with it
19 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.
- package.json 932 B
- src/access-reset.ts 3.3 KB runs code
- src/api-command.ts 5.9 KB runs code
- src/args.ts 7.5 KB runs code
- src/index.ts 15 KB runs code
- src/install.ts 489 B runs code
- src/pair.ts 3.6 KB runs code
- src/status.ts 5.1 KB runs code
- test/access-reset.test.ts 2.3 KB runs code
- test/api-command.test.ts 4.6 KB runs code
- test/args.test.ts 5.6 KB runs code
- test/install-script-copy.test.ts 946 B runs code
- test/install.test.ts 9.8 KB runs code
- test/pair.test.ts 2.8 KB runs code
- test/run.test.ts 13 KB runs code
- test/status.test.ts 6.7 KB runs code
- tsconfig.build.json 112 B
- tsconfig.json 180 B
- tsup.config.ts 182 B runs code
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.
- yesterday First seen · 32 lines · 21 tokens per session scan A 7e2dbe8e1b6f
roamcode-command-center is a skill published in the GitHub repository burakgon/roamcode (19 stars, last pushed 3d ago), licensed MIT. It adds 21 tokens to every session and 426 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 2026-08-30.
Other skills, from other repositories
verify-pr
This skill should be used to run a sandboxed deep verification of a qwen-code PR — "/verify-pr ", "深度验证这个 PR", A/B load-bearing proof against the base build, mock-free harnesses with wire oracles, and targeted gates — producing tmp/pr -verify- /report.md plus a machine-readable verdict. Designed for the token-free CI…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
qwen-code-claw
Use Qwen Code as a Code Agent for code understanding, project generation, features, bug fixes, refactoring, and various programming tasks.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…