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 archyl-com/agent-skills --skill archyl-predictgit clone --depth 1 https://github.com/archyl-com/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/archyl-com/agent-skills/archyl-predict)<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>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 | $0.00040 | $0.08144 |
| Opus 5 | $0.00020 | $0.04072 |
| Sonnet 5 | $0.00008 | $0.01629 |
| Haiku 4.5 | $0.00004 | $0.00814 |
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.
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)
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.
- 7d ago First seen · 724 lines · 40 tokens per session scan A 609fa3b027f2
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.
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…
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…
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…
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…