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 skills add okisdev/claude-code-fusion --skill smokegit clone --depth 1 https://github.com/okisdev/claude-code-fusionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/okisdev/claude-code-fusion/smoke)<a href="https://agentmods.dev/skills/okisdev/claude-code-fusion/smoke"><img src="https://agentmods.dev/badge/skills/okisdev/claude-code-fusion/smoke/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/okisdev/claude-code-fusion/smoke"><img src="https://agentmods.dev/badge/skills/okisdev/claude-code-fusion/smoke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00657 |
| Opus 5.5 | $0.00010 | $0.00263 |
| Sonnet 5.5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
smoke 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 10d 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.
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
Verify the update landed, then prove the dispatch chain end to end with four tiny probes before real packages ride it.
- Version parity: read
~/.claude/plugins/installed_plugins.jsonand compare the fusion, codex, grok, and cursor entries against.claude-plugin/marketplace.jsonin this repository when present. Report each version pair; a mismatch is a FAIL naming the stale plugin. - Fan out four probes as parallel foreground Agent calls in one message. The three engine probes name no model, so the routing table's lane default fills it and the probe exercises that path too:
- a
codex:codex-rescuetask whose direct prompt passes--effort low --cwd "<absolute repository root>" --followed by a brief whose header line islane: codex volume | effort low | acceptance: exact marker lineand whose body asks for exactly the line FUSION-SMOKE-CODEX-OK; - a
grok:grok-rescuetask whose direct prompt passes--effort low --cwd "<absolute repository root>" --followed by a brief whose header line isgrok-role: burst | effort low | acceptance: exact marker lineand whose body asks for exactly the line FUSION-SMOKE-GROK-OK; - a
cursor:cursor-rescuetask whose direct prompt passes--cwd "<absolute repository root>" --followed by a brief whose header line iscursor-role: diversity | acceptance: exact marker lineand whose body asks for exactly the line FUSION-SMOKE-CURSOR-OK; - a
fusion:trivial-workerbrief in thefusion-brief: v1envelope withcontext-mode: isolated, a goal of returning exactly the line FUSION-SMOKE-WORKER-OK, a scope of no file access, and an acceptance of the exact marker line.
- a
- Collect all four, then settle them in one
/fusion:statscall carrying one--record <id>=<verdict>flag per probe: accepted only when the exact marker line came back, rejected otherwise. - Report one PASS or FAIL line per gate: version parity, codex dispatch and envelope, grok dispatch and sandbox handshake, cursor dispatch and private home, worker dispatch and deliverable, settlement write. The codex, grok, and cursor gates also require the lane default notice naming the filled model, and the cursor gate also requires that the job record's
homeDirsits under the Cursor plugin'sruns/directory. A FAIL names the failing surface and advises holding real dispatches on that lane until repaired.
The wave is a probe, not work: never attach real packages to it, and never skip the settlement step, because the settlement write is itself one of the gates under test.
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.
- 10d ago Changed · +1 lines a85b17da3d44
- 25d ago Changed · +3 lines 25a8df2780a3
- 1mo ago First seen · 17 lines · 25 tokens per session scan A 4e147e01f0fa
smoke is a skill published in the GitHub repository okisdev/claude-code-fusion (3 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 657 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
qa-lead
Quality assurance consultation for Conductor orchestrator. Sets test coverage requirements, validates quality gates, determines testing strategy. Can adjust coverage thresholds within ranges. Escalates skipping critical tests to Board of Directors.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
eval-integration
Specialized integration evaluator for the Evaluate-Loop. Use this for evaluating tracks that integrate external services — Supabase auth/DB, Stripe payments, Gemini API, third-party APIs. Checks API contracts, auth flows, data persistence, error recovery, environment config, and end-to-end flow integrity. Dispatched…
eval-business-logic
Specialized business logic evaluator for the Evaluate-Loop. Use this for evaluating tracks that implement core product logic — pipelines, dependency resolution, state machines, pricing/tier enforcement, packaging. Checks feature correctness against product rules, edge cases, state transitions, data flow, and user…
eval-code-quality
Specialized code quality evaluator for the Evaluate-Loop. Use this for evaluating code implementation tracks where the deliverable is functional code — features, API routes, state management, utilities. Checks build integrity, type safety, code patterns, error handling, dead code, imports, test coverage, and naming…
loop-executor
Evaluate-Loop Step 3: EXECUTE. Use this agent to implement tasks from a verified plan. Works through plan.md tasks sequentially, writes code, updates plan.md after every task, and commits at checkpoints. Uses TDD where applicable. Triggered by: 'execute plan', 'implement track', 'build feature', '/conductor implement'…