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 tetracoralla/context-surface-analyzer --skill analyze-context-surfacegit clone --depth 1 https://github.com/tetracoralla/context-surface-analyzerWrote 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/tetracoralla/context-surface-analyzer/analyze-context-surface)<a href="https://agentmods.dev/skills/tetracoralla/context-surface-analyzer/analyze-context-surface"><img src="https://agentmods.dev/badge/skills/tetracoralla/context-surface-analyzer/analyze-context-surface.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 | $0.00082 | $0.00281 |
| Opus 5 | $0.00041 | $0.00140 |
| Sonnet 5 | $0.00016 | $0.00056 |
| Haiku 4.5 | $0.00008 | $0.00028 |
Grade A, and why
analyze-context-surface 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.
What it actually says
Analyze Context Surface
Call context.analyze for one context-surface.snapshot.v0.1 document and
context.diff for an earlier and later snapshot. The selected tool exposes the
complete input schema. Use exactly one domain-tool call for an ordinary valid
request and return a stable tool error without inventing a fallback for invalid
input.
Require an explicit snapshot from the current provider, host, or authorized exporter. Do not claim that a repository fixture is the current installed catalog, and do not ask this utility to inspect the host or filesystem.
Present exact structural facts concisely. Canonical UTF-8 bytes are not token estimates. Duplicate schemas mean exact canonical equality, and collisions mean exact case-sensitive repeated names; neither establishes semantic redundancy or product value. Compare token measurements only when every identity label matches. Never recommend routing, disablement, retirement, or acceptance from this result alone.
What ships with it
1 file 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.
- 7d ago First seen · 24 lines · 82 tokens per session scan A 70953b81c180
analyze-context-surface is a skill published in the GitHub repository tetracoralla/context-surface-analyzer (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 82 tokens to every session and 281 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 2026-08-31.
Other skills, from other repositories
meituan-deals
A Meituan assistant for finding food deals, collecting coupons, and placing restaurant group-buy orders. Meituan is a Chinese local-services platform for dining and other everyday purchases.
Tencent Cloud Infra
A command-line guide for managing Tencent Cloud services, including servers, networks, domains, certificates, storage, permissions, and monitoring. Tencent Cloud is a cloud provider, and tccli is its command-line tool.
source-verify
A source-checking workflow for confirming that medical information comes from an authoritative, complete, and currently valid document.
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
octop-assistant
A configuration assistant for Octop, a service that runs AI agents and connects them to messaging channels. It helps manage models, providers, channels, skills, scheduled tasks, backups, upgrades, and agent-specific settings.
wechat-publisher-personal
A personal publishing skill that turns one Markdown article into posts for a Chinese content platform and RedNote, a Chinese social-media platform. It formats the long article for the first platform and adapts it into a shorter post with images and hashtags for RedNote.