archyl-predict

archyl-predict is a skill for Claude Code from archyl-com/agent-skills. It costs 40 tokens per session (8,144 once invoked), scanned A, original, MIT.

A forecasting tool for software architecture health. It uses past drift, delivery performance, compliance, system complexity, relationships, and change history to identify likely future risks.

In plain words
What is it for?
Reviewing architecture trends, forecasting drift and complexity, examining delivery-performance trajectories, and finding risks that may need preventive action.
Why use it?
It helps teams notice worsening architecture or delivery patterns before they become larger problems. The results support preventive planning rather than only reacting to failures.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the archyl-developer plugin — 10 skills, 1 hook shipped together

Good fit Reviewing architecture trends, forecasting drift and complexity, examining delivery-performance trajectories, and finding risks that may need preventive action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/archyl-com/agent-skills/archyl-predict
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.

Any agent
npx skills add archyl-com/agent-skills --skill archyl-predict
Clone the repo
git clone --depth 1 https://github.com/archyl-com/agent-skills

Made for: Claude Code.

Or install archyl-developer, the plugin that ships this one along with the rest of its 10 skills, 1 hook.

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 archyl-predict

README.md
[![agentmods](https://agentmods.dev/badge/skills/archyl-com/agent-skills/archyl-predict.svg)](https://agentmods.dev/skills/archyl-com/agent-skills/archyl-predict)
Your own site
<a href="https://agentmods.dev/skills/archyl-com/agent-skills/archyl-predict"><img src="https://agentmods.dev/badge/skills/archyl-com/agent-skills/archyl-predict.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,144 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00040 $0.08144
Opus 5 $0.00020 $0.04072
Sonnet 5 $0.00008 $0.01629
Haiku 4.5 $0.00004 $0.00814

Measured 7d ago against content hash 609fa3b027f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

archyl-predict 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 7d 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.

plugins/archyl-developer/skills/archyl-predict/SKILL.md · 724 lines

How it starts

The opening of the file, as written. The whole thing — 724 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Archyl Predict

You are a predictive architecture analyst. You analyze historical trends from Archyl -- drift scores, DORA metrics, conformance results, and C4 model complexity -- to forecast risks and recommend preventive actions before problems materialize. You turn trailing indicators into leading ones.

You interact with Archyl exclusively through MCP tool calls prefixed with mcp__archyl__.

Quick Start

Every prediction session begins the same way:

1. list_projects          -> find the target project (you need a projectId)
2. get_drift_history      -> drift trend over time
3. get_dora_trend         -> DORA time-series (weekly or monthly)
4. get_conformance_stats  -> current compliance snapshot
5. list_conformance_checks -> compliance over time
6. get_project_c4_model   -> current complexity (elements, relationships)
7. list_relationships     -> coupling analysis
8. list_history           -> change velocity and pattern
9. list_insights          -> existing AI insights (avoid duplicating)

Always start with list_projects. You need a projectId for every operation.

Prediction Engine

The engine operates across 5 analysis dimensions. Each dimension produces forecasts with explicit confidence levels and timeframes.

Confidence Levels

Confidence depends on data availability:

Data Available Confidence Label
>90 days of history HIGH Strong trend signal, reliable 90-day projection
30-90 days of history MEDIUM Reasonable 30-day projection, 90-day is speculative
<30 days of history LOW Insufficient for reliable projection, report current state only

Always state the confidence level and the amount of historical data behind each prediction.

Dimension 1: Drift Trajectory

Goal: Project when drift will cross critical thresholds.

Data sources:

get_drift_history(projectId)   -> drift scores over time
get_drift_score(scoreId)       -> latest drift score (if no history, compute one first)

Read the full file on GitHub · 724 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. 7d ago First seen · 724 lines · 40 tokens per session scan A 609fa3b027f2

Subscribe to this mod's changes

archyl-predict is a skill published in the GitHub repository archyl-com/agent-skills (2 stars, last pushed 12d ago), licensed MIT. It adds 40 tokens to every session and 8,144 once invoked, about $0.0002 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 2026-08-31.

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-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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens