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 GuitarAlchemist/ga --skill sentrux-next-stepsgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/sentrux-next-steps)<a href="https://agentmods.dev/skills/guitaralchemist/ga/sentrux-next-steps"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/sentrux-next-steps/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/guitaralchemist/ga/sentrux-next-steps"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/sentrux-next-steps.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 | $0.00126 | $0.03677 |
| Opus 5 | $0.00063 | $0.01839 |
| Sonnet 5 | $0.00025 | $0.00735 |
| Haiku 4.5 | $0.00013 | $0.00368 |
Grade A, and why
sentrux-next-steps 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 9d 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.
Endpoint fallback (curl against the running Vite dev server, port 5176): How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sentrux-next-steps
Closes the "raw metrics, no prescription" gap on the Sentrux dashboard
tab. Today operators see quality_signal=3015, 632 cycles, 6.8% coverage and a bottleneck label — useful but not directive. This skill
converts those numbers into a ranked list of refactor + coverage moves with
starter sketches, persists them to state/quality/sentrux-next-steps/,
and the SentruxNextStepsCard component on /test#dev/sentrux renders
the result at the top of the tab.
Invoked as /sentrux-next-steps from any Claude Code session, or queued
via the Regenerate button on the Sentrux Next Steps card (which POSTs
to /actions/harness/skill/sentrux-next-steps — an agent picks it up).
Sister skills:
/test-plan— diff-driven test proposals for an open PR (forward-looking)./grade-last-pr— intent-vs-delivery on the merged PR (backward-looking)./sentrux-next-steps— structural-quality refactor proposals (this skill, ambient — fires on demand or daily).
Together they answer:
/test-plan— what should I test on this PR?/grade-last-pr— did the last PR deliver what its title said?/sentrux-next-steps— what should I refactor next, period?
When to run
- When the Sentrux Next Steps card is empty or stale (last generation
7 days). The card surfaces last-generated timestamp; operators hit Regenerate when the data feels old.
- After a large structural change merges — the cycle count and quality_signal shift; the prior recommendations may be moot. Re-run to refresh the prescription.
- At the start of a refactor sprint — gives the team a written, ranked menu instead of "let's grep for cycles and see".
- Daily via workflow (future) — the same skill can fire on a cron
to keep
latest.mdfresh without operator action. Today the skill is manual-only.
Do NOT invoke for:
- A repo with no sentrux scan history — the recommendations would be
speculation. Run
mcp__sentrux__scanfirst and verifyhealthreturns a number. - Hot-fix branches — this is a strategic prescription, not a debugging
aid. Use
/octo:debugfor "why is this broken right now?". - Pure docs/CI sprints — sentrux measures code structure; recommending cycle-breaks on a documentation-only push is noise.
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.
- 9d ago First seen · 324 lines · 126 tokens per session scan A 9aefc243990f
sentrux-next-steps is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 3,677 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…