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 SophonMe/AIContext --skill aicontext-ingestgit clone --depth 1 https://github.com/SophonMe/AIContextWrote 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/sophonme/aicontext/aicontext-ingest)<a href="https://agentmods.dev/skills/sophonme/aicontext/aicontext-ingest"><img src="https://agentmods.dev/badge/skills/sophonme/aicontext/aicontext-ingest.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 | $0.00034 | $0.01169 |
| Opus 5 | $0.00017 | $0.00584 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
aicontext-ingest 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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIContext Data Ingestion Skill
What This Skill Does
Given a base data path from the user, you explore the directory, identify ingestible data sources, and implement DataSource classes that parse them into AIContext's unified activity database.
This skill handles one-time static ingestion only. All data sources
created through this skill are registered as "mode": "static" — they are
ingested once and skipped by the hourly sync daemon. This is the correct
approach for data exports (Google Takeout, Amazon data downloads, ChatGPT
export, etc.) that are snapshots in time.
If a user asks to ingest a dynamic data source (one that updates
continuously, e.g., a local app database, browser history), do not
implement it through this skill. Instead, explain that dynamic sources
must be implemented directly in aicontext/sources/ within the AIContext
package and registered in aicontext/sources/__init__.py, then guide the
user to do so.
Exploring the AIContext Source Code
You are encouraged to read the actual aicontext source code for deeper
understanding beyond what protocol.md covers. To find the installed
package location:
python3 -c "import aicontext; import os; print(os.path.dirname(aicontext.__file__))"
Key files worth reading:
sources/base.py-- the DataSource ABC you're implementing againstrecords.py-- ActivityRecord and ReferenceFile dataclassestimestamps.py-- timestamp parsing helpers you can importingester.py-- how ingestion, validation, and dedup worksources/-- existing built-in sources as reference implementations
Workflow
- Read
protocol.mdto understand the DataSource interface and conventions - Explore the user-provided base path to discover what data is present
- Match discoveries against guides in
sources/for known formats - Ask the user to confirm which sources to ingest and the exact paths
- Read the relevant guide(s) in
sources/<name>.md - Examine the actual data files to understand the exact format
- Implement DataSource class(es) in
~/.aicontext/data_sources/<source_key>.py - Add entries to
~/.aicontext/config.json - Tell the user to run
aicontext syncto ingest
What ships with it
11 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.
- protocol.md 7.6 KB
- sources/.gitkeep 0 B
- sources/amazon_browsing.md 1.2 KB
- sources/amazon_cart.md 862 B
- sources/amazon_media.md 2.2 KB
- sources/amazon_orders.md 2.0 KB
- sources/amazon_search.md 1.6 KB
- sources/chatgpt.md 3.0 KB
- sources/claude_web.md 2.6 KB
- sources/google_chrome_history.md 1.7 KB
- sources/google_takeout_activity.md 5.4 KB
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.
- 8d ago First seen · 119 lines · 34 tokens per session scan A 6f59ef8d147c
aicontext-ingest is a skill published in the GitHub repository SophonMe/AIContext (9 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,169 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
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
binder-import
Import external data into a Binder workspace. Handles CSV, JSON, YAML, Markdown files, and directories of Markdown. Use when asked to "import data", "load records from a file", "ingest documents", "migrate data into binder", or bulk-create records from an external source.
turingdb-graph
Build, query, and analyse biomedical knowledge graphs in TuringDB, a columnar graph database with git-like versioning.
scrna-orchestrator
Local Scanpy pipeline for single-cell RNA-seq QC, optional doublet detection, clustering, marker discovery, optional CellTypist annotation, optional latent downstream mode from integrated.h5ad/Xscvi, and optional dataset-level plus within-cluster contrastive marker analysis from raw-count .h5ad or 10x Matrix Market…
scrna-embedding
Local scVI/scANVI-based single-cell latent embedding and batch-aware integration from raw-count .h5ad or 10x Matrix Market input, with stable integrated AnnData export for downstream latent analysis.
bigquery-public
Run read-only SQL against BigQuery public datasets with local result capture, cost safeguards, and reproducibility outputs.