adios-operate-debug

A set of instructions for diagnosing and operating Adios workspaces, preview environments, builds, and deployed workloads. It defines an evidence-first process for checking workspace state, Git status, logs, source files, and configuration.

In plain words
What is it for?
Use it to inspect workspace and run status, read the right logs, check files such as adios.yaml and dependency manifests, and perform changes only when a fix is requested.
Why use it?
It helps an agent locate whether a failure comes from a command, build, runtime, deployment, or configuration instead of guessing.

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/adiosdotdev/mcp/adios-operate-debug
Any agent
npx skills add adiosdotdev/mcp --skill adios-operate-debug
Clone the repo
git clone --depth 1 https://github.com/adiosdotdev/mcp

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 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 $0.00075 $0.00629
Opus 5 $0.00037 $0.00315
Sonnet 5 $0.00015 $0.00126
Haiku 4.5 $0.00007 $0.00063

Measured yesterday against content hash 7ba07d37228c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adios-operate-debug 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.

plugins/adios-mcp/skills/adios-operate-debug/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Operate and Debug Adios

Use an evidence-first diagnostic flow. Start with read-only tools, identify the failing layer, and mutate runtime or source state only when the user requests a fix.

Diagnostic workflow

  1. Call auth_me and establish team_id. Resolve the target using get_workspace or list_workspaces; do not guess a workspace or workload ID.
  2. Establish current state with get_workspace, get_workspace_run_status, and get_workspace_git_status.
  3. Choose logs that match the failure:
    • Use get_workspace_command_status and get_workspace_command_logs when a command_id exists.
    • Use get_workspace_logs with type=build for build failures.
    • Use get_workspace_logs with type=runtime for preview startup or runtime failures.
    • Use get_workload_logs for a deployed workload.
  4. Read only the source files implicated by the evidence using list_workspace_files and read_workspace_file. Common first checks are adios.yaml, dependency manifests, lock files, and the runtime entrypoint.
  5. Run check_workspace_adios_yaml for manifest or startup problems. Use security_review_workspace only to collect review context; inspect the returned Git and file evidence before making a security judgment.
  6. State the most likely cause, cite the tool evidence, and distinguish confirmed facts from hypotheses.
  7. If the user asked for a fix, make the smallest change, rerun the relevant command, poll it to completion, and verify runtime status and logs.

Operational actions

  • Prefer restart_workspace_run after a verified configuration or source fix.
  • Use run_workspace_command only when the specialized lint, build, start, stop, or restart tool does not fit.
  • Poll long-running commands instead of issuing duplicates. Include relevant log excerpts in the summary without exposing secrets.
  • Ask for explicit approval before stop_workspace_run, file deletion, or deployment. Pass approved=true only after approval.

Guardrails

  • Do not treat missing logs as proof of health. Report the gap and inspect status or the adjacent log surface.
  • Do not reveal access tokens, secrets, or complete sensitive environment values found in logs or files.
  • Do not turn a diagnostic request into a source edit, restart, stop, or deploy without authorization.
  • If OAuth is expired or the principal lacks team access, ask the user to re-authenticate or select an authorized team.

Read the full file on GitHub · 41 lines

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. yesterday First seen · 41 lines · 75 tokens per session scan A 7ba07d37228c

Subscribe to this mod's changes

adios-operate-debug is a skill published in the GitHub repository adiosdotdev/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 629 once invoked, about $0.0004 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

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

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

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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