prompt-update

prompt-update is a skill for Claude Code from rakovi4/continue-framework. It costs 39 tokens per session (805 once invoked), scanned B, original, MIT.

A documentation workflow for deciding where a new rule, code example, detection pattern, or process step belongs in a project’s prompt documentation. It then writes the information into the relevant documentation layers.

In plain words
What is it for?
Use it to add or update project instructions, coding principles, code-smell detection rules, reusable templates, and layer-specific guidance.
Why use it?
It prevents useful guidance from being added to the wrong file or recorded without the checks needed to apply it. It also makes the classification explicit before documentation is changed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Install

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.

agentmods
npx agentmods add skills/rakovi4/continue-framework/prompt-update
Any agent
npx skills add rakovi4/continue-framework --skill prompt-update
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/rakovi4/continue-framework/prompt-update.svg)](https://agentmods.dev/skills/rakovi4/continue-framework/prompt-update)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 805 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.00805
Opus 5 $0.00019 $0.00402
Sonnet 5 $0.00008 $0.00161
Haiku 4.5 $0.00004 $0.00081

Measured 6d ago against content hash 8cb5752cdca8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 6d 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?
.claude/skills/prompt-update/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 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

  1. Parse input. If no content provided, ask the user what to add.
  2. Understand the content. What does it mean? Is it a principle, a detection pattern, a code example, a workflow step?
  3. Classify targets using .claude/templates/documentation/prompt-update-classification.md. Walk ALL 4 decision questions explicitly — principle, detection pattern, code example, layer-specific context. Show the classification before writing:
    1. Principle? → .claude/guidelines/frontend-rules.md (new section)
    2. Detection? → code-smells-routing-table.md (smell table) + scan-duplication.md (A-check)
    3. Template?  → new templates/refactoring/extract-tailwind-class.md
    4. Layer-specific? → n/a
    
    Most updates touch 2+ files. If only one target is identified, double-check — a rule without detection won't be enforced, a detection without a template won't guide the fix.
  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?
  5. Write to all target files in one pass. Match each file's existing style.
  6. 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.
  7. 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/.
  8. Report what was written and where (see Output format in classification template).
  9. Verify with /skill-creator — see Impact Assessment in classification template.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 6d ago First seen · 53 lines · 39 tokens per session scan B 8cb5752cdca8

Subscribe to this mod's changes

prompt-update is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 805 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens