smoke

A local end-to-end check for the explainCode endpoint, which receives a code snippet and returns an explanation. It starts the Worker development server, sends a sample request, and checks that the response is not empty.

In plain words
What is it for?
Use it to verify that the local Worker responds correctly before deploying or after modifying the code-explanation feature.
Why use it?
It catches missing secrets, startup failures, and broken endpoint responses after code changes.

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/billduke13/code-explainer-mcp/smoke
Any agent
npx skills add BillDuke13/code-explainer-mcp --skill smoke
Clone the repo
git clone --depth 1 https://github.com/BillDuke13/code-explainer-mcp

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 553 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 $0.00039 $0.00553
Opus 5 $0.00019 $0.00277
Sonnet 5 $0.00008 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 2d ago against content hash 7d922ad10d48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

smoke 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.

for _ in $(seq 1 30); do curl -sf -o /dev/null http://localhost:8787 && break; sleep 1; done
.claude/skills/smoke/SKILL.md · 43 lines

What it actually says

Smoke-test the explainCode endpoint

Verify the Worker handles a real explainCode request end to end against the local dev server.

Steps

  1. Resolve the secret (never print it). Load .dev.vars so $SHARED_SECRET is set:

    set -a; [ -f ./.dev.vars ] && . ./.dev.vars; set +a
    

    The Worker fails closed: if SHARED_SECRET is unset or still the YOUR_SECRET_KEY_HERE placeholder, every request returns 503. Stop and tell the user to put a real secret in .dev.vars before smoke-testing:

    case "${SHARED_SECRET:-}" in '' | YOUR_SECRET_KEY_HERE) echo 'Set a real SHARED_SECRET in .dev.vars first'; exit 1 ;; esac
    
  2. Start the dev server if it isn't already listening on port 8787. Launch npm run dev in the background, then poll until the port answers (bounded to ~30s; fail if it never comes up):

    for _ in $(seq 1 30); do curl -sf -o /dev/null http://localhost:8787 && break; sleep 1; done
    curl -sf -o /dev/null http://localhost:8787 || { echo 'dev server did not start within 30s'; exit 1; }
    
  3. Send a sample request (use the snippet/language from CLAUDE.local.md if set):

    curl -sS -X POST http://localhost:8787 \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $SHARED_SECRET" \
      -d '{"method":"explainCode","params":["function add(a, b) { return a + b; }","javascript"]}'
    
  4. Check the result: the response must be JSON with a non-empty result string. Report PASS/FAIL and show the first few lines of result. On FAIL (non-200, missing result, or an error field), surface the status code and body.

  5. Clean up: stop the dev server you started in step 2 (kill the background wrangler dev process). Do not stop a server the user already had running.

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 · 43 lines · 39 tokens per session scan A 7d922ad10d48

Subscribe to this mod's changes

smoke is a skill published in the GitHub repository BillDuke13/code-explainer-mcp (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 553 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 2026-08-31.

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

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