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/templatesgit 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/templates)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/templates"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/templates.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 | $0.00986 | $0.00986 |
| Opus 5 | $0.00493 | $0.00493 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
ai-agents templates.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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Template File Rules
templates/ is the source of truth for the agent copies that build/generate_agents.py writes: src/copilot-cli/agents/ and src/vs-code-agents/. It does NOT cascade everywhere. src/claude/, .claude/agents/, and .github/agents/ are hand-maintained and no generator writes them, so a template edit reaches them only if you make the matching edit yourself in the same change. Forgetting either half leaves the platforms out of sync.
MUST
- Regenerate after edits. Changes MUST be followed by running
uv run python build/generate_agents.pybefore commit. Uncommitted generator output is a protocol failure. - Commit generated output. Regenerated files under
src/copilot-cli/agents/andsrc/vs-code-agents/MUST be committed in the same PR as the template change. Those two are the only treesbuild/generate_agents.pywrites;src/claude/,.claude/agents/, and.github/agents/are hand-maintained and the generator does not touch them (see.agents/governance/GENERATOR-FILES.md). - Toolset integrity. Changes that add or remove tools MUST update
templates/toolsets.yamlconsistently. - Frontmatter fields. Agent templates MUST keep
descriptionpresent and valid.nameis not a template field: no shipped agent template defines it, and the generator derives the generated agent's name from the template's own filename before platform conversion, adding it back only for a platform whose config setsincludeNameField: true.model_tieris optional: ADR-080 governs whether a generated agent may carry amodel:pin at all (see MUST-5). ADR-002, formerly cited here, is deprecated in favor of ADR-080 (2026-08-25). - Model selection. A template's
model_tierMUST comply with ADR-080. The generator resolves amodel:pin for the generated Copilot/VS Code/Visual Studio mirrors in two cases only: a fresh, fully-validatedKEEP_PINentry in the ADR-080 sidecar manifest for that template (ADR-080 rules 2 and 4, any tier), or thehaikutier with no such entry, the sole cost exception ADR-080 rule 3 recognizes. When no valid manifest entry exists,model_tier: opusormodel_tier: sonnet, and nomodel_tierat all, MUST resolve to nomodel:field, so the mirror inherits the harness default rather than shipping an unjustified pin that breaks on the next model retirement (issue #5313).
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 · 34 lines · 986 tokens per session scan A 83bd4831827b
ai-agents templates.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 986 tokens to every session, about $0.0049 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).