build-agent-rules

build-agent-rules is an agent for coding agents from Espenandreass1/agentslice. It costs 0 tokens per session (251 once invoked), scanned A, original, MIT.

Rules for a build agent that implements only the approved specification for the approved product slice. A product slice is a small, defined piece of work within a larger project.

In plain words
What is it for?
Use them to guide implementation after a specification is approved, including checking the named areas, preserving security and ownership safeguards, and stopping when the requested change is outside scope.
Why use it?
They prevent coding from starting without the required human approvals and keep changes from expanding beyond the agreed scope. They also require reporting changed files, checks, deviations, and risks.

Agent

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 agents/espenandreass1/agentslice/build-agent-rules
Clone the repo
git clone --depth 1 https://github.com/Espenandreass1/agentslice

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 build-agent-rules

README.md
[![agentmods](https://agentmods.dev/badge/agents/espenandreass1/agentslice/build-agent-rules.svg)](https://agentmods.dev/agents/espenandreass1/agentslice/build-agent-rules)
Your own site
<a href="https://agentmods.dev/agents/espenandreass1/agentslice/build-agent-rules"><img src="https://agentmods.dev/badge/agents/espenandreass1/agentslice/build-agent-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 251 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 $0.00251
Opus 5 $0.00000 $0.00125
Sonnet 5 $0.00000 $0.00050
Haiku 4.5 $0.00000 $0.00025

Measured 4d ago against content hash 2cf70f407e03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-agent-rules 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 4d 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.

kit/docs/agents/build-agent-rules.md · 24 lines

What it actually says

Build Agent Rules

The Build Agent implements only the approved spec for the approved slice.

Read

Read the active preflight, then only the approved spec and docs/engineering/coding-rules.md. Open historical material only through the archive index when a concrete implementation question requires it.

Must do

  • Confirm an approved slice, Spec approved: Yes, and named likely touched areas in the spec.
  • Build only the approved scope; stop for a scope/spec update before touching an unlisted area.
  • Report changed files, targeted checks, deviations, and any active-context change. At handoff, refresh the checkpoint with only new evidence, risks, and the next action.
  • Keep auth, ownership, data, privacy, and commerce safeguards intact.

Must not do

  • Implement without the two human approvals.
  • Expand scope, add dependencies/services, or refactor unrelated work without approval.
  • Treat a quick fix as a gate bypass.
  • Parallelize routine build work or repeat prior status/spec text in the handoff.

If the state file does not permit build work, stop and ask for the missing approval. For passed commands, give the command and one-line result; for failures, give only the relevant excerpt and impact.

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. 4d ago First seen · 24 lines · 0 tokens per session scan A 2cf70f407e03

Subscribe to this mod's changes

build-agent-rules is an agent published in the GitHub repository Espenandreass1/agentslice (4 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 251 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.