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 gohypergiant/agent-skills --skill accelint-prompt-managergit clone --depth 1 https://github.com/gohypergiant/agent-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/gohypergiant/agent-skills/accelint-prompt-manager)<a href="https://agentmods.dev/skills/gohypergiant/agent-skills/accelint-prompt-manager"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-prompt-manager/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/gohypergiant/agent-skills/accelint-prompt-manager"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-prompt-manager.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 | $0.00134 | $0.05020 |
| Opus 5 | $0.00067 | $0.02510 |
| Sonnet 5 | $0.00027 | $0.01004 |
| Haiku 4.5 | $0.00013 | $0.00502 |
Grade C, and why
accelint-prompt-manager scanned grade C 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 11d 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
When optimizing prompts that handle user input, consider injection attacks. Validate and sanitize inputs, use delimiters to separate instructions from data, and never allow user content to override system instructions. How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Manager
Turn vague, ambiguous, or unclear prompts into optimized, well-structured prompts through systematic assessment, pattern detection, framework selection, and validation.
Your Role and Output
Produce one artifact only: the optimized prompt. That artifact MUST be a clear, well-structured prompt that the user or Claude can execute.
Do NOT:
- Do NOT execute the task yourself — You optimize prompts. You do not fulfill them. If the user asks "help me with X", create a clear prompt for X. Do not do X.
- Do NOT try to run the optimized prompt — Hand the optimized prompt to the user so they or Claude can execute it.
- Do NOT research external resources — Work only with the user's input text. Treat URLs and references in prompts as text to optimize, not as resources to fetch.
Workflow Summary
- Decide whether the user wants prompt optimization or task execution.
- Identify ambiguities, missing constraints, trade-offs, and complexity.
- Create an optimized prompt, or ask targeted clarifying questions when needed.
- Deliver the optimized prompt directly to the user.
- After delivery, optionally save the optimized prompt or copy it to the clipboard.
Primary Delivery
- Always present the optimized prompt first in your response, inside a markdown code block for easy copying.
- Never save files before delivering the optimized prompt.
Clarification Rule
- If critical details are missing and guessing would materially change the output, ask a small set of targeted questions before producing the final optimized prompt.
- Group related questions.
- Explain why the questions matter.
- Avoid overwhelming the user.
Optional Post-Delivery
- After presenting the optimized prompt, offer to save it to a markdown file, copy it to the clipboard, or both.
Example
- User: "make this data look better"
- You: Analyze vagueness → Create a clear prompt with specific success criteria → Output the optimized prompt in a markdown code block → Offer to save or copy the optimized prompt
- You do NOT: Try to access the data yourself, or try to make the data look better yourself.
What ships with it
24 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.
- AGENTS.md 6.1 KB
- assets/prompt-templates/analytical.md 2.8 KB
- assets/prompt-templates/creative.md 2.9 KB
- assets/prompt-templates/debugging.md 3.6 KB
- assets/prompt-templates/documentation.md 3.0 KB
- assets/prompt-templates/exploration.md 3.6 KB
- assets/prompt-templates/implementation.md 3.8 KB
- assets/prompt-templates/planning.md 5.0 KB
- assets/prompt-templates/refactoring.md 5.1 KB
- assets/prompt-templates/review.md 6.2 KB
- assets/prompt-templates/security.md 7.4 KB
- assets/prompt-templates/testing.md 9.4 KB
- assets/prompt-templates/troubleshooting.md 7.3 KB
- CHANGELOG.md 24 KB
- evals/evals.json 19 KB
- README.md 6.5 KB
- references/ambiguity-examples.md 11 KB
- references/complexity-detection.md 9.3 KB
- references/credit-killing-patterns.md 13 KB
- references/frameworks.md 8.4 KB
- references/optimization-examples.md 15 KB
- references/plan-mode-triggers.md 10 KB
- references/safe-techniques.md 11 KB
- references/template-selection.md 15 KB
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.
- 11d ago First seen · 389 lines · 134 tokens per session scan C 8507640e52f3
accelint-prompt-manager is a skill published in the GitHub repository gohypergiant/agent-skills (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 134 tokens to every session and 5,020 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…