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 instructions/jnpiyush/agentx/aigit clone --depth 1 https://github.com/jnPiyush/AgentXWhat 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 | $0.00807 | $0.00807 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
AgentX ai.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 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI & Agent Development Instructions
Auto-loads when editing agent/LLM/workflow files. For comprehensive standards, load the skill.
Skill: .github/skills/ai-systems/ai-agent-development/SKILL.md
Quality Loop Gate (read before editing)
Before editing any agent definition, prompt, workflow, or LLM-integration file, run .agentx/agentx.ps1 loop start -p "<task>" as your ABSOLUTE FIRST tool call. Close with .agentx/agentx.ps1 loop complete -s "<summary>" once a subagent review iteration has passed. The pre-commit hook blocks commits when the loop is missing or incomplete. See .github/copilot-instructions.md for the full rule.
Mandatory Workflow Gates (read before editing)
Four additional rules carry the same weight as the Quality Loop and are hard-failed by the pre-commit hook:
- Compound Capture: APPROVED review staged -> matching
docs/artifacts/learnings/LEARNING-<issue>.mdMUST also be staged, or commit msg tagged[skip-capture]. - Model Council (MANDATORY, NO SKIP): New
docs/artifacts/adr/ADR-*.mdstaged -> matchingdocs/artifacts/adr/COUNCIL-*.mdMUST also be staged (3 diverse models + Synthesis). Mandatory for Product Manager (prd-scope), Architect (adr-options), and any complex task; also Data Scientist (ai-design), Reviewer (code-review), Consulting Research. The pre-commit hook hard-fails when the COUNCIL file is missing; there is no skip token. - Execution Plan: Commits changing >= 8 code files MUST stage a matching
docs/execution/plans/EXEC-PLAN-*.md, or commit msg tagged[skip-plan]. - Brainstorm (Engineer):
Research -> Brainstorm -> Plan -> ...pipeline is mandatory; Brainstorm step is satisfied by abrainstormledger entry or## Alternatives Consideredin the execution plan before Plan.
See .github/copilot-instructions.md for the canonical block.
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 · 45 lines · 807 tokens per session scan A f55eeab69e17
AgentX ai.instructions.md is an instructions file published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 807 tokens to every session, about $0.0040 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.
Other instructions, from other repositories
MarkdownLLM Framework
A self-describing specification framework for building LLM-driven systems using markdown, YAML, and git.
SkillOpt AGENTS.md
Instructions for mitkox/SkillOpt, covering agent instructions for skillopt, project identity, default example workflow, documentation expectations and repo hygiene.
ai-prompts AGENTS.md
Instructions for liatrio-labs/ai-prompts, covering ai agent instructions, context marker, local skill scripts, standard workflow and initialize.
CacheLane CLAUDE.md
Instructions for Aditya-Tripuraneni/CacheLane, covering cachelane — project context for claude/agent sessions, where to start, source documents and per-milestone implementation workflow (lean).
drift drift-prompt-engineering.instructions.md
Nutze diese Instruction, wenn Prompts, Instructions, Skills, Agents oder Copilot-Customization in Drift erstellt, geschärft oder reviewt werden. Fokus: discovery-taugliches Frontmatter, enge applyTo-Scopes, Shared-Partials-Wiederverwendung, Artefaktvertraege und Anti-Halluzinationsregeln fuer Prompt-Engineering.
github-copilot-use-cases copilot-instructions.md
Instructions for amir0135/github-copilot-use-cases, covering github copilot instructions and use cases, general copilot best practices, code generation, prompt engineering and common use cases.