linkedin.asisaga.com github-docs.instructions.md

A set of rules for documentation files in .github/docs/, a folder for guides and reference material used by the agent system.

In plain words
What is it for?
Use it when creating guides, tutorials, troubleshooting notes, examples, or reference documents for the agent system.
Why use it?
It gives documentation a consistent structure, naming style, audience information, and separation from specifications or coding rules.

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/asisaga/linkedin.asisaga.com/github-docs
Clone the repo
git clone --depth 1 https://github.com/ASISaga/linkedin.asisaga.com

Made for: GitHub Copilot.

Per session 593 This file is loaded in full into every session.
When invoked 593 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 $0.00593 $0.00593
Opus 5 $0.00296 $0.00296
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00059 $0.00059

Measured yesterday against content hash d77636448b32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

linkedin.asisaga.com github-docs.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/github-docs.instructions.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Files Standards

Purpose

Documentation files in .github/docs/ are implementation guides and references that help users understand and use the agent intelligence system.

File Naming

  • Use kebab-case: guide-name.md
  • Be descriptive: agent-system-overview.md not overview.md
  • Include type: getting-started-guide.md, api-reference.md

Content Structure

# Documentation Title

**Last Updated**: YYYY-MM-DD  
**Audience**: [Developers | Contributors | Users]

## Introduction
[What this document covers]

## Prerequisites
[What you need to know before reading]

## Content
[Main documentation content]

## Examples
[Practical examples]

## Next Steps
[What to read/do next]

## References
[Related docs and specs]

Content Guidelines

DO Include:

  • Step-by-step guides
  • Tutorials and walkthroughs
  • Usage examples
  • Troubleshooting tips
  • Quick reference materials

DON'T Include:

  • Detailed specifications (belong in .github/specs/)
  • Path-specific coding standards (belong in .github/instructions/)
  • Duplicate content from other docs

Documentation Types

Guides: How to accomplish specific tasks

  • getting-started-guide.md
  • migration-guide.md

References: Quick lookup information

  • agent-quick-reference.md
  • api-reference.md

Overviews: System understanding

  • agent-system-overview.md
  • architecture-overview.md

Cross-References

Docs should be:

  • Referenced from: copilot-instructions.md, instruction files, specs
  • Reference: Specs for technical details
  • Link to: Other related docs

Validation

Before committing:

  1. Follows naming convention
  2. Has clear audience and prerequisites
  3. Examples are tested and work
  4. Links to other docs/specs are correct
  5. No duplication with specs or instructions

Agent framework: .github/specs/agent-intelligence-framework.md - Complete system specification
Architecture: /docs/specifications/architecture.md - System architecture and organization
Agent guidelines: /docs/specifications/github-copilot-agent-guidelines.md - Standards and best practices
Self-learning: /docs/specifications/agent-self-learning-system.md - Dogfooding and Ouroboros
Agent philosophy: .github/docs/agent-philosophy.md - Core principles

Read the full file on GitHub · 101 lines

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 · 101 lines · 593 tokens per session scan A d77636448b32

Subscribe to this mod's changes

linkedin.asisaga.com github-docs.instructions.md is an instructions file published in the GitHub repository ASISaga/linkedin.asisaga.com (0 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 593 tokens to every session, about $0.0030 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.

Related

Other instructions, from other repositories