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/plugin-self-containmentgit 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/plugin-self-containment)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/plugin-self-containment"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/plugin-self-containment.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 | $0.03828 | $0.03828 |
| Opus 5 | $0.01914 | $0.01914 |
| Sonnet 5 | $0.00766 | $0.00766 |
| Haiku 4.5 | $0.00383 | $0.00383 |
Grade A, and why
ai-agents plugin-self-containment.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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Self-Containment
The boundary
Three directories ship as installable plugins. Nothing else in this repository reaches a consumer.
| Plugin root | Plugin name | Marketplace |
|---|---|---|
.claude/ |
project-toolkit |
.claude-plugin/marketplace.json |
src/claude/ |
claude-agents |
.claude-plugin/marketplace.json |
src/copilot-cli/ |
project-toolkit |
.github/plugin/marketplace.json |
Each marketplace entry names exactly one source directory. A consumer who installs the plugin receives that directory and nothing above it. docs/, .agents/, build/, scripts/, templates/, and the repository root stay behind.
templates/agents/** is in scope for this rule because it is the canonical source that generates shipped agent files. An outward reference introduced there lands in a plugin root on the next build.
Three kinds of path, only one of which is a defect
The distinction below is the whole rule. Getting it wrong in either direction is expensive.
| Kind | Example | Verdict |
|---|---|---|
| Bundled dependency: a file the plugin ships and must resolve at runtime | a sibling skill's script under the same plugin root | Fine. Address it through the plugin-root env vars. |
| Consumer-workspace path: a location in the installing repository that the agent reads or writes | an agent told to write its output to .agents/planning/ or docs/adr/ in the consumer's repo |
Fine. This is the plugin doing its job. Not a defect. |
Upstream-only dependency: a path that exists only in rjmurillo/ai-agents |
templates/agents/security.shared.md, docs/agent-catalog.md, build/scripts/build_all.py |
Defect, unless declared. Dangles for every consumer. |
A grep cannot tell these apart. A reviewer can. When the target exists only upstream and the text instructs the reader to open, run, or resolve it, that is the defect.
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 · 181 lines · 3,828 tokens per session scan A fcd1236288dd
ai-agents plugin-self-containment.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 3,828 tokens to every session, about $0.0191 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.
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).
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.