conductai copilot-instructions.md

conductai copilot-instructions.md is an instructions file for GitHub Copilot from sseshachala/conductai. It costs 458 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for ConductAI that require an activity log and policy check during agent conversations.

In plain words
What is it for?
They guide agents on when to record user activity, check request intent, protect secrets, and avoid sending personal data externally.
Why use it?
They help apply ConductGuard rules consistently, including stopping blocked requests and warning about risky ones.

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/sseshachala/conductai/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/sseshachala/conductai

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for conductai copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sseshachala/conductai/copilot-instructions.svg)](https://agentmods.dev/instructions/sseshachala/conductai/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/sseshachala/conductai/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sseshachala/conductai/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 458 This file is loaded in full into every session.
When invoked 458 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 $0.00458 $0.00458
Opus 5 $0.00229 $0.00229
Sonnet 5 $0.00092 $0.00092
Haiku 4.5 $0.00046 $0.00046

Measured 3d ago against content hash 6a9369056146, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conductai copilot-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 3d 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.

.github/copilot-instructions.md · 40 lines

What it actually says

ConductGuard Policy

At the start of every conversation:

  • Call guard_activity ONCE with a one-line summary of what the user is asking.

Then, for the request itself:

  • Call guard_check ONCE per intent — not per file, per command, or per edit.
  • Re-check only when scope changes (reads → writes, local → network, or a new task).
  • If BLOCKED: stop and explain the policy rule to the user.
  • If WARNING: proceed but surface the warning inline.
  • If the response is ok or empty: proceed silently. Do NOT narrate it in the chat.

Example:

  1. User asks to fix a bug → call guard_activity once with the summary.
  2. Before starting the code changes → call guard_check once with the intent (e.g. write_file, bash).
  3. Do NOT re-check for every subsequent read or edit in the same task.

Never write secrets to files or output. Never send PII to external endpoints.

ConductGuard Policy

At the start of every conversation:

  • Call guard_activity ONCE with a one-line summary of what the user is asking.

Then, for the request itself:

  • Call guard_check ONCE per intent — not per file, per command, or per edit.
  • Re-check only when scope changes (reads → writes, local → network, or a new task).
  • If BLOCKED: stop and explain the policy rule to the user.
  • If WARNING: proceed but surface the warning inline.
  • If the response is ok or empty: proceed silently. Do NOT narrate it in the chat.

Example:

  1. User asks to fix a bug → call guard_activity once with the summary.
  2. Before starting the code changes → call guard_check once with the intent (e.g. write_file, bash).
  3. Do NOT re-check for every subsequent read or edit in the same task.

Never write secrets to files or output. Never send PII to external endpoints.

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. 3d ago First seen · 40 lines · 458 tokens per session scan A 6a9369056146

Subscribe to this mod's changes

conductai copilot-instructions.md is an instructions file published in the GitHub repository sseshachala/conductai (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 458 tokens to every session, about $0.0023 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.