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 glebis/claude-skills --skill the-goalgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/the-goal)<a href="https://agentmods.dev/skills/glebis/claude-skills/the-goal"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/the-goal/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/glebis/claude-skills/the-goal"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/the-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00184 | $0.01820 |
| Opus 5 | $0.00092 | $0.00910 |
| Sonnet 5 | $0.00037 | $0.00364 |
| Haiku 4.5 | $0.00018 | $0.00182 |
Grade A, and why
the-goal 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Goal — constraint-first automation
Named after Eliyahu Goldratt's The Goal. The lesson this skill encodes: a local optimum is not a global one. Automating something that feels productive but is not the system's constraint produces no throughput gain. Most wasted automation effort dies here. This skill finds the constraint first, then points exactly one automation at it.
When to use
Use before building anything, and during reviews:
- "What should I automate?" / "Where do I point my agents?" / "What's the highest-leverage thing right now?"
- The user is about to build a Claude Code skill, Goal, loop, schedule, or workflow and isn't sure it matters.
- The user has a pile of half-useful automations and feels busy but stuck.
- A periodic review of where agent effort is going.
If the user already knows their constraint with confidence and just wants to build, skip the diagnosis and go straight to Step 4 (elevate) and the Recommendation.
The core distinction (state this early)
Three ways an automation idea fails, worst first:
- It targets a non-constraint. The worst kind. Even a flawless automation here adds zero throughput; the bottleneck still caps the system. Cut it.
- It optimizes a local metric. Feels productive (inbox zero, faster research) but the global goal does not move.
- "Felt busy" is not "moved the needle." Activity is not throughput. Require a measurable throughput before recommending anything.
Workflow — the Five Focusing Steps
Run as an interactive diagnostic, one focused question at a time. The LLM's job is to elicit the picture and map it to structured inputs; two scripts then do the ranking and the rung selection deterministically, so the core calls aren't free-form vibes. Load references/five-focusing-steps.md for the full method, definitions (throughput / inventory / operating expense in knowledge-work terms, drum-buffer-rope, Herbie) and example walkthroughs.
Optional — cenno mode. If cenno is available and the user prefers panels (or asks to "ask me in panels"), collect the inputs through cenno instead of chat: choice 0–3 (or a custom a2ui 0–3 slider) for the ordinal scores, confirm for necessary_condition/policy_gate and the seven rung facts, text for the goal/throughput. The answers feed the same two scripts unchanged. Load references/cenno-mode.md for the control mapping, ask_sequence batching, and how to persist the analysis. Fall back to chat if cenno isn't running — never block.
What ships with it
6 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.
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.
- 8d ago First seen · 80 lines · 184 tokens per session scan A 44d04af28fcc
the-goal is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 184 tokens to every session and 1,820 once invoked, about $0.0009 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 2026-09-03.
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…