invocation-templates

invocation-templates is a cursor rule for coding agents from robertsfeir/atelier-pipeline. It costs 3,926 tokens per session, scanned A, original, Apache-2.0.

A set of Cursor rules containing reusable instructions for invoking agents, including templates for producing architecture decision records and research briefs.

In plain words
What is it for?
It is for running predefined agent templates such as standard or research-backed ADRs, where an ADR records an important architecture decision and its reasoning.
Why use it?
It standardizes how agents receive context, read shared references, record timing, and perform recurring documentation or investigation tasks.

Cursor rule

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/robertsfeir/atelier-pipeline/invocation-templates
Clone the repo
git clone --depth 1 https://github.com/robertsfeir/atelier-pipeline

Wrote 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.

agentmods badge for invocation-templates

README.md
[![agentmods](https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/invocation-templates.svg)](https://agentmods.dev/rules/robertsfeir/atelier-pipeline/invocation-templates)
Your own site
<a href="https://agentmods.dev/rules/robertsfeir/atelier-pipeline/invocation-templates"><img src="https://agentmods.dev/badge/rules/robertsfeir/atelier-pipeline/invocation-templates.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,926 This file is loaded in full into every session.
When invoked 3,926 The same file — it is already loaded in full.
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 $0.03926 $0.03926
Opus 5 $0.01963 $0.01963
Sonnet 5 $0.00785 $0.00785
Haiku 4.5 $0.00393 $0.00393

Measured 5d ago against content hash c1a7700f29be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

invocation-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 5d 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.

.cursor-plugin/rules/invocation-templates.mdc · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invocation Templates

Shared Protocols (apply to all templates below)

Brain-context injection: Eva prefetches via agent_search and injects into <brain-context>. Domain-specific captures handled automatically by the brain-extractor SubagentStop hook after each agent completion. Omit tag when brain unavailable.

Standard READ items (included in every invocation, not listed per template): .cursor/references/retro-lessons.md, .cursor/references/agent-preamble.md

Persona constraints apply: Templates list only task-specific constraints that supplement the persona. Do not duplicate persona-level rules.

Telemetry timing: Eva records start_time/end_time around every Agent tool invocation. duration_ms = end_time - start_time.


Template Index

# Template ID Agent Purpose
1 sarah-adr Sarah ADR production (standard)
2 sarah-adr-large Sarah ADR production with research brief (medium/large)
2a scout-research-brief Explore+haiku (x3) Pre-Sarah research scouts (medium+large)
2b codebase-investigation Explore+haiku (xN) → Sonnet reviewer Ad-hoc codebase scan: partition by area, collect evidence, synthesize
2c scout-synthesis Sonnet Post-scout filter/rank/trim before primary agent
3 colby-mockup Colby UI mockup with mock data
4 colby-build Colby Build unit; CI Watch variant: scope to CI fix
10 ellis-commit Ellis Wave commit
11 agatha-writing Agatha Documentation writing
12 robert-acceptance Robert Product acceptance review
13 sable-acceptance Sable UX acceptance review
14 poirot-blind Poirot Blind wave diff review
15 sentinel-audit Sentinel Security audit (Semgrep-backed)
16 deps-scan Deps Full dependency scan
17 deps-migration-brief Deps Migration ADR brief
18 distillator-compress Distillator Lossless document compression
19 distillator-validate Distillator Compression with round-trip validation
20 darwin-analysis Darwin Pipeline telemetry analysis

Read the full file on GitHub · 327 lines

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. 5d ago First seen · 327 lines · 3,926 tokens per session scan A c1a7700f29be

Subscribe to this mod's changes

invocation-templates is a cursor rule published in the GitHub repository robertsfeir/atelier-pipeline (25 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,926 tokens to every session, about $0.0196 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.