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 Arenukvern/skill_steward --skill vision-alignment-foresightgit clone --depth 1 https://github.com/Arenukvern/skill_stewardWrote 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/arenukvern/skill_steward/vision-alignment-foresight)<a href="https://agentmods.dev/skills/arenukvern/skill_steward/vision-alignment-foresight"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/vision-alignment-foresight/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/arenukvern/skill_steward/vision-alignment-foresight"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/vision-alignment-foresight.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 | $0.00080 | $0.01349 |
| Opus 5 | $0.00040 | $0.00674 |
| Sonnet 5 | $0.00016 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
vision-alignment-foresight 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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Alignment Foresight
Test whether a vision is still worth building, not just whether it sounds coherent.
Use this skill to connect four things that often drift apart: stated intent, real implementation, observed evidence, and future direction.
Trigger Examples
- Should trigger: "Analyze this vision against the app and future agent direction."
- Should trigger: "Does our repo strategy still make sense given current usage and platform changes?"
- Should trigger: "Criticize this roadmap and predict where it will fail."
- Should not trigger: "Write an ADR for this accepted decision." Use
repository-governance-lifecycle. - Should not trigger: "Run a broad multi-agent critique only." Use
mixture-of-experts.
Workflow
-
Name the intent.
- Restate the human goal in one or two sentences.
- Separate the durable purpose from the proposed implementation.
- Mark what is explicit, inferred, and unknown.
-
Map the application reality.
- Read the North Star, ADRs, FAQs, skill docs, config, harness entrypoints, tests, and release notes that define current behavior.
- Identify the actual user, maintainer, agent, and runtime surfaces.
- Record any contradiction between docs, code, config, and user behavior.
-
Collect evidence.
- Prefer concrete signals: usage logs, eval results, issue/PR history, support questions, benchmark outcomes, adoption friction, failing tests, repeated manual workflows, and rollback history.
- If future direction matters, do current research using primary sources where possible.
- Label every major claim as observed, researched, inferred, or speculative.
-
Run critical lenses.
- Product/user lens: who benefits, who pays the complexity cost, what workflow improves?
- Engineering lens: what must be true in code, tests, data, deploys, and interfaces?
- Agent experience lens: can another agent discover, execute, verify, and recover without hidden context?
- Maintenance lens: what will decay, fork, or become impossible to support?
- Ecosystem/future lens: does the plan align with platform movement, standards, and likely integration paths?
- Adversarial lens: what evidence would prove the vision wrong?
What ships with it
4 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.
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.
- 9d ago First seen · 139 lines · 80 tokens per session scan A 7b265a87afad
vision-alignment-foresight is a skill published in the GitHub repository Arenukvern/skill_steward (11 stars, last pushed 24d ago), licensed MIT. It adds 80 tokens to every session and 1,349 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.
iflytek-pdf-image-ocr
AI-powered OCR service for images and PDF documents using iFlytek's advanced recognition APIs.
iflytek-voiceclone-tts
A tool for creating a speech model from recorded audio and then generating speech that uses the cloned voice. Voice cloning means training software to imitate a person’s voice.
animated-sketch-diagram
A tool for making animated diagrams and flowcharts in a hand-drawn ink style, with paper-like backgrounds, simple icons, and moving dots along connections. It produces a self-contained HTML file and can also create a looping GIF.
iflytek-text-proofread
A tool that checks Chinese writing through iFlytek’s official document-proofreading service. It looks for spelling, punctuation, wording, factual, terminology, and sensitive-content problems.