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/rjmurillo/ai-agents/generated-artifactsgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/generated-artifacts)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/generated-artifacts"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/generated-artifacts.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 | $0.02826 | $0.02826 |
| Opus 5 | $0.01413 | $0.01413 |
| Sonnet 5 | $0.00565 | $0.00565 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
ai-agents generated-artifacts.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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer-Facing Generated Artifacts
This rule exists because of a P0 incident. A generator produced the Copilot CLI
plugin's hooks.json with a bare ./hooks/... command path and explicit
cwd: ".". Copilot CLI 1.0.57 resolved that path from the user's working
directory, not the plugin install directory, so every hook failed at launch
with "No such file or directory". The failure happened before any in-script
handler could run. The only recovery was to uninstall the plugin. The broken
form shipped for 33 days across six releases (v0.3.0 to v0.5.6). See
.agents/retrospective/2026-06-02-pr-2205-customer-wedge-incident.md.
Current official docs define hook cwd relative to the repository root or as
an absolute path. The Copilot CLI changelog documents plugin-root variables.
The historical incident still controls our design: generated launchers anchor
plugin files explicitly and never depend on ambient cwd.
The root cause was not the wrong path. It was that a customer-facing artifact shipped without ever being executed in its target runtime. Every test validated the artifact's structure (valid JSON, correct fields). None ran the artifact under the real runtime contract.
This rule binds any generator that emits an artifact installed into a customer's
environment: plugin manifests and hooks.json, copied hook scripts, agent and
skill files a CLI loads, MCP configs, instruction mirrors. It does not bind
artifacts consumed only inside this repo's own CI.
The paths globs target every authoring, generated, and verification surface:
agents, skills, commands, prompts, rules, hooks, templates, generators, plugin
trees, and runtime-contract tests. This ensures future work loads the settled
harness contract before changing any artifact class.
The runtime contract is part of the artifact
Every customer-facing artifact depends on a runtime contract: the working directory the host sets, the environment variables it exports, the process model (shell, interpreter on PATH), and the target tool and version. That contract is as load-bearing as the artifact's bytes.
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.
- yesterday First seen · 224 lines · 2,826 tokens per session scan A 4698f1cdc684
ai-agents generated-artifacts.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 2,826 tokens to every session, about $0.0141 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 2026-09-03.
Other instructions, from other repositories
abtars AGENTS.md
AGENTS.md instructions for aksika/abtars, covering agents.md, quick commands, architecture, model-call chokepoint: spin(spec) (#1271) and external dependency: abmind.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
gameforge AGENTS.md
Instructions for robcost/gameforge, covering general guidelines for working with nx, scaffolding & generators and when to use nxdocs.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).