agent-templates

A set of rules for writing agent template files, which define how specialized coding agents behave.

In plain words
What is it for?
Use it when creating or updating agent templates, especially review agents that must report findings without fixing code themselves.
Why use it?
It keeps agents within clear boundaries and makes review agents consistent about tone, source-code reading, and escalation.

Cursor rule for Claude Code

Install

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.

agentmods
npx agentmods add rules/aimeerrhythm/enterprise-change-workflow/agent-templates
Clone the repo
git clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflow

Made for: Claude Code.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 294 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00294
Opus 5 $0.00000 $0.00147
Sonnet 5 $0.00000 $0.00059
Haiku 4.5 $0.00000 $0.00029

Measured yesterday against content hash 176a29921815, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-templates 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.

.claude/rules/agent-templates.mdc · 35 lines

What it actually says

Agent Template Conventions

Subagent Boundary Guard (ALL agents)

Every agent template MUST include a ## Subagent Boundary section with:

  • Prohibit invoking any ecw: skills (skills are orchestrator-level capabilities)
  • Prohibit spawning additional subagents via Agent tool (leaf node principle)
  • Prohibit loading or reading SKILL.md files (instructions are self-contained)
  • Report BLOCKED/NEEDS_CONTEXT status when encountering orchestrator-level situations

Anti-Sycophancy (Review agents only)

Review agents (spec-reviewer, domain-analyst, domain-negotiator, impl-verifier) MUST include a ## Review Tone section:

  • No pleasantries — state findings directly
  • No impact → say so bluntly without hedging
  • High impact → state problems without softening
  • Never open with praise or caveats — lead with the assessment

Source Code Reading Limits (Review agents only)

Review agents MUST include a ## Source Code Reading Limits section:

  • Set explicit file read cap (e.g., max 10 source files)
  • Prefer Grep with limited context (-A 5) over full Read
  • Only Read full files for core interfaces directly participating in the change
  • Knowledge files do NOT count toward the file limit
  • Purpose: prevent token explosion and irrelevant code wandering
Changes

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.

  1. yesterday First seen · 35 lines · 0 tokens per session scan A 176a29921815

Subscribe to this mod's changes

agent-templates is a cursor rule published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 294 tokens. 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 2026-08-31.