Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rakovi4/continue-framework/main/.claude/skills/prompt-update/SKILL.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/prompt-update)<a href="https://agentmods.dev/skills/rakovi4/continue-framework/prompt-update"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/prompt-update/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/rakovi4/continue-framework/prompt-update"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/prompt-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 29 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00039 | $0.00754 |
| Opus 5.5 | $0.00016 | $0.00302 |
| Sonnet 5.5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade B, and why
prompt-update scanned grade B 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
4. **Check for duplication** — grep key terms across `.claude/rules/`, `.claude/tech/`, `.claude/agents/`, `.claude/skills/`, `.claude/templates/`. If a duplicate exists, report it and ask: skip, merge, or replace? How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-update - Classify & Place Documentation Content
Classify a piece of new content and write it to the correct file(s) in the project's documentation layers.
Usage
/prompt-update "always use eq() not any() in Mockito"
/prompt-update "test-review should catch Fake storage assertions"
/prompt-update # Interactive — asks what to add
Workflow
- Parse input. If no content provided, ask the user what to add.
- Understand the content. What does it mean? Is it a principle, a detection pattern, a code example, a workflow step?
- Classify targets using
.claude/templates/documentation/prompt-update-classification.md. Check every category: principle → rules/guidelines; technology-specific detail → tech binding; detection/workflow → agent; example → template; layer-specific context → skill or template. Update every applicable owner; one file is enough when no other layer needs a change. Briefly report the chosen targets and why. - Check for duplication — grep key terms across
.claude/rules/,.claude/tech/,.claude/agents/,.claude/skills/,.claude/templates/. If a duplicate exists, report it and ask: skip, merge, or replace? - Make the smallest sufficient edit. Prefer revising an existing sentence or bullet over adding a section. Add examples, exceptions, or checklists only when needed to resolve ambiguity. Match the file's existing style.
- Tech-agnostic gate — for every write targeting a universal file (
.claude/rules/,.claude/templates/), scan the content you just wrote for tech leaks. See "Tech-Agnostic Verification" in the classification template. If a leak is found, rephrase in universal terms first — only relocate to tech binding when the content is inherently tech-specific. - Product-agnostic gate — after writing, re-read every edit you made (all layers, not just universal) and scrub product-specific information: product/company name, business-domain terms, external vendor/integration names, concrete domain entity names, and story/feature names or numbers. Replace each with the generic concept it represents. See "Product-Agnostic Verification" in the classification template. The prompt library must be reusable across products; product instances belong only in
ProductSpecification/. - Review and report. Remove repetition and text that adds no distinct instruction, then briefly report what changed and where.
- Verify with
/skill-creator— see Impact Assessment in classification template.
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.
- 1mo ago Changed · -7 lines b65ce561fc2e
- 2mo ago First seen · 53 lines · 39 tokens per session scan B 8cb5752cdca8
prompt-update is a skill published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 39 tokens to every session and 754 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…