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/project-conventionsgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/instructions/jnpiyush/agentx/project-conventions)<a href="https://agentmods.dev/instructions/jnpiyush/agentx/project-conventions"><img src="https://agentmods.dev/badge/instructions/jnpiyush/agentx/project-conventions.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 | $0.00536 | $0.00536 |
| Opus 5 | $0.00268 | $0.00268 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
AgentX project-conventions.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 4d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Conventions (Learned)
This always-on file is a router. Detailed cross-cutting rules live in AGENT-PROTOCOL.md; agent definitions MUST link to that file instead of repeating it.
Required Rules
- Before any code/docs mutation, start the quality loop as the first tool call.
Meet the CLI's risk-based minimum and end with a structured subagent review
verdict (
loop iterate ... --verdict approved --reviewer <id> --high 0 --medium 0), thenloop complete. Checkloop statusbefore reporting gate state. - Load and follow the Karpathy guidelines for implementation/review. Run
.agentx/agentx.ps1 scrub -Path <changed-area>before review or handoff. - Engineer work follows
Research -> Brainstorm -> Plan -> Design -> Implement -> Scrub -> Test -> Review. Record alternatives before Plan. - New ADRs require a matching Model Council artifact. Approved reviews require matching learning capture or the documented skip rationale. Changes to eight or more code files require an execution plan or documented skip token.
- UI work defaults to browser validation: primary routes, axe scan, and one primary interaction. Report unavailable browser prerequisites instead of silently skipping.
- Agent
model:fields and named council models are advisory. Preserve role behavior across capable models and preserve each agent's tool/permission boundaries. - AgentX is zero-copy. Initialize through
agentx.initializeLocalRuntime; never copy bundled agent, skill, instruction, template, guide, or prompt trees into a workspace.
Working Conventions
- Prefer small
apply_patchedits with enough context to identify the target. - After structural edits, search for removed identifiers and run the narrowest executable check before widening validation.
- PowerShell
ConvertTo-Jsoncan flatten single-element arrays; wrap with@(...). - Passing unit tests does not replace validation of UI, wiring, or release boundaries.
- Keep durable decisions and pitfalls concise in
/memories/; keep this router short.
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.
- 4d ago First seen · 49 lines · 536 tokens per session scan A b34b65cd4c91
AgentX project-conventions.instructions.md is an instructions file published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed today), licensed Apache-2.0. It adds 536 tokens to every session, about $0.0027 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.