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 agentmods add skills/asteasolutions/ai-toolkit/project-contextnpx skills add asteasolutions/ai-toolkit --skill project-contextgit clone --depth 1 https://github.com/asteasolutions/ai-toolkitWhat 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 | $0.00038 | $0.00557 |
| Opus 5 | $0.00019 | $0.00279 |
| Sonnet 5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
project-context 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context
Workflow
- Ask the user: "Which project?" If the project name is clear from context, skip the ask.
- Run the freshness check:
If the output says docs are stale or missing, warn the user before continuing:node .claude/skills/project-context/scripts/check-freshness.js <project>- Stale (>24 h):
"Docs for [project] were last synced [X hours/days] ago. They may be out of date — run /docs-generator to refresh." - Missing:
"No docs found for [project]. Run /docs-generator to generate them first."Continue regardless — stale docs are better than no answer.
- Stale (>24 h):
- Ask: "What are you looking for?" — a keyword, feature area, or issue number.
- Run:
The script prints matching file paths and excerpts. If no keyword, it lists all files. If it returns no matches, retry once withnode .claude/skills/project-context/scripts/search-project-docs.js <project> "<keyword>"--fuzzy(matches the keyword's characters in order, tolerating typos or partial recall) before concluding there's nothing relevant. One search is usually enough. Only run a second exact search with a related term if the first returns fewer than 5 results. - Read the relevant files in full and answer the user's question.
- When the answer concerns a specific task or issue, cite the issue tracker as the source of truth, not the synced doc.
Script reference
check-freshness.js <project>
project Folder name under docs/
Output: staleness status — "ok", "stale", or "missing" — with age in hours.
Exit 0 always (stale docs are still usable).
search-project-docs.js <project> [keyword] [--fuzzy] [--case-sensitive]
project Folder name under docs/
keyword Optional. Search term. Matches file name or content.
--fuzzy Subsequence match instead of substring — use as a fallback when an
exact search returns nothing, to tolerate typos or partial recall.
--case-sensitive Disable the default case-insensitive matching.
Output: matching file paths + first matching line with context.
Exit 1 if the project folder does not exist.
What ships with it
3 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.
- 2d ago First seen · 53 lines · 38 tokens per session scan A 0ee13c388dba
project-context is a skill published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 557 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
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
sn-da-large-file-analysis
万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl readonly 流式读取（iterrows 支持 10 万行以上）、Parquet 转换加速、内存优化、分块处理和大文件写入模式。遇到以下任一情况就主动使用本 skill：①数据行数 ≥ 10k（由 sn-da-excel-workflow 的行数评估步骤触发）；②用户出现触发词：大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing；③直接使用…
resilient-document-pipeline
Unified document generation with tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety.
category-filtering-and-difficulty-analysis
对Excel数据进行自定义分类统计、交叉分析与可视化，并基于多维度指标（如文本长度、术语密度、正则匹配等）进行综合评分与分级，适用于多类别数据分布统计及文本内容难度/质量评估场景。.
summarize-document
Summarize a long PDF, scan, office file, text file, or markdown file through the connected Superlinked MCP edge instead of reading the whole source into model context. Use when the user asks for a summary, overview, digest, or "what does this document say" about a large file.