contextweaver sensitivity.instructions.md

Security instructions for ContextWeaver's data-sensitivity module. The module classifies and removes or hides data before it is sent through the context pipeline to the AI model.

In plain words
What is it for?
Use them when modifying sensitivity classification, redaction, default filtering, or other code that controls what data reaches the model.
Why use it?
Changes to data filtering can accidentally expose information to the model. These instructions require conservative defaults and extra review for security-sensitive changes.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/dgenio/contextweaver/sensitivity
Clone the repo
git clone --depth 1 https://github.com/dgenio/contextweaver

Made for: GitHub Copilot.

Per session 121 This file is loaded in full into every session.
When invoked 121 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00121 $0.00121
Opus 5 $0.00060 $0.00060
Sonnet 5 $0.00024 $0.00024
Haiku 4.5 $0.00012 $0.00012

Measured yesterday against content hash 6b3d8e3ff2c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextweaver sensitivity.instructions.md 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 yesterday.

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.

.github/instructions/sensitivity.instructions.md · 15 lines

What it actually says

Sensitivity Enforcement — Security-Grade Code

This module enforces data classification and redaction in the context pipeline. Treat all changes as security-sensitive:

  • Never weaken defaults. The default sensitivity floor and default drop action are deliberately conservative.
  • Extra review scrutiny required. Changes here affect what data reaches the LLM.
  • Do not refactor for "simplicity." The current structure exists to enforce safety invariants. See docs/agent-context/invariants.md for rationale.
Changes

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.

  1. yesterday First seen · 15 lines · 121 tokens per session scan A 6b3d8e3ff2c7

Subscribe to this mod's changes

contextweaver sensitivity.instructions.md is an instructions file published in the GitHub repository dgenio/contextweaver (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 121 tokens to every session, about $0.0006 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.