agentmods.dev

intent-engineering AGENTS.md

Repository instructions for working on the intent-engineering Claude Code plugin. They explain the project structure, rules, and how its review process works.

In plain words
What is it for?
Use them when contributing to the intent-engineering repository, especially when editing its skills, review lenses, documentation, or contract files.
Why use it?
They give coding agents the background needed to change the plugin without breaking its installable structure or internal conventions.

Instructions file for CodexOpenCode

3 16d ago A scan 4,819 tokens original MIT
View the source file davidteren/intent-engineering
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 instructions/davidteren/intent-engineering/agents-md
Clone the repo
git clone --depth 1 https://github.com/davidteren/intent-engineering

Made for: Codex, OpenCode.

Per session 4,819 This file is loaded in full into every session.
When invoked 4,819 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 $0.04819 $0.04819
Opus 5 $0.02410 $0.02410
Sonnet 5 $0.00964 $0.00964
Haiku 4.5 $0.00482 $0.00482

Measured 2d ago against content hash a818c955e1c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intent-engineering AGENTS.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 2d 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.

AGENTS.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working in the intent-engineering repo

Guidance for any AI agent (or human) contributing to this repository. Read this before editing. CLAUDE.md points here; this is the single source of truth for how the repo is laid out and the rules that keep the plugin installable and internally consistent.

This repo develops the intent-engineering Claude Code plugin. The plugin's own end-user docs live in plugins/intent-engineering/README.md; the design lives in PLAN.md, current state in STATUS.md, and change history in CHANGELOG.md.

What this repo is

A Claude Code plugin that enforces intent engineering: software that behaves the way a reasonable developer or user already expects. It applies established design principles as review lenses (parallel sub-agents) across four contexts — planning, plan validation, code review, codebase audit — producing scored, deduplicated, confidence-gated findings with concrete fixes.

The plugin is data + prompts, not executable code. Skills and agents are markdown that the model follows; the knowledge base and contract files are markdown/JSON/YAML. There is no build step and no runtime. "Correctness" here means the prose contracts, schemas, and cross-references stay mutually consistent.

Load-bearing rules (break these and the plugin breaks)

  1. agents/ gitignore trap. Some environments globally ignore agents/ everywhere (several AI coding tools add it to a global gitignore). The repo .gitignore MUST keep the !plugins/intent-engineering/agents/ + !plugins/intent-engineering/agents/** negation, or on such a machine all five lens agents silently leave git and a cloned plugin has zero agents. It's defensive — keep it so the plugin is portable regardless of a contributor's global config. After touching anything under agents/, verify with git ls-files plugins/intent-engineering/agents/ (expect 5 files). The same lesson is why .idea/ is listed in the repo .gitignore too.
  2. Self-contained plugin. Everything the installed plugin needs lives under plugins/intent-engineering/ — agents/, skills/, references/, config/, resources/. A Claude Code plugin only ships what's inside its plugin dir. Never move resources/ or references/ to the repo root. Edit them in place; they are the single source of truth. Optional Grok runtimes live in repo-root .grok/workflows/ and must not be moved into the plugin dir.
  3. Runtime paths use ${CLAUDE_PLUGIN_ROOT}. Every cross-file reference inside a skill or agent must address shipped files as ${CLAUDE_PLUGIN_ROOT}/<dir>/<file> — never a bare filename or repo-relative path. A lens runs in isolation and can only resolve ${CLAUDE_PLUGIN_ROOT} paths.
  4. Read-only by default; never push. Lenses are read-only except for the Layer A run-scratch JSON write. Orchestrators write the published report under docs/intent-engineering/ (and clean up run scratch). Only /ie-review (interactive) mutates product code — applies safe fixes, commits on a clean tree — and /ie-init writes under .intense/ (optional .gitignore append for runs). Nothing ever pushes, opens PRs, or files tickets.
  5. Two-layer artifacts — not wip/. Run scratch → .intense/runs/<run-id>/ (lens JSON; deleted after publish when cleanup_runs: true). Published report → docs/intent-engineering/<stamp>-<skill>[-scope].md. Configure via artifacts.* in ways-of-working.yaml. Do not reintroduce plugin defaults under wip/ or .wip/.
  6. ie- prefix for every skill and agent. Project config dir is .intense/.

Read the full file on GitHub · 316 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. 2d ago First seen · 316 lines · 4,819 tokens per session scan A a818c955e1c7

Subscribe to this mod's changes

intent-engineering AGENTS.md is an instructions file published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed 16d ago), licensed MIT. It adds 4,819 tokens to every session, about $0.0241 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 2026-08-31.

Code reviewFrontendWriting and docsauditclaude-codeclaude-code-pluginconvention-over-configurationdesign-principles
Related

Other instructions, from other repositories

jentic-one GEMINI.md

Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.

jentic/jentic-one · 51 tokens

hig-doctor AGENTS.md

AGENTS.md instructions for raintree-technology/hig-doctor: HIG Doctor combines open-source audit tooling with an attributed snapshot of Apple's Human Interface Guidelines.

raintree-technology/hig-doctor · 146 tokens

briefloop AGENTS.md

Instructions for Stahl-G/briefloop, covering agents.md, purpose, instruction scope, environment separation and context mode.

Stahl-G/briefloop · 2,496 tokens

ProofFlow-v0.1 AGENTS.md

Instructions for Hyperion-GPU/ProofFlow-v0.1, covering proofflow agent rules, workflow, evidence, safety and architecture.

Hyperion-GPU/ProofFlow-v0.1 · 484 tokens

obsigna python.instructions.md

Instructions for agent-receipts/obsigna, a project described as: Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.

agent-receipts/obsigna · 113 tokens

goshipit CLAUDE.md

Instructions for Capta1nRaj/goshipit, covering goshipit - project instructions, sync rule (enforce after every change), how to count checks, git commits and package.json description format.

Capta1nRaj/goshipit · 667 tokens