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/intent-integrity-chain/kit/agents-mdgit clone --depth 1 https://github.com/intent-integrity-chain/kitWhat 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 | $0.01874 | $0.01874 |
| Opus 5 | $0.00937 | $0.00937 |
| Sonnet 5 | $0.00375 | $0.00375 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
kit 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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Integrity Kit
Closing the intent-to-code chasm
Overview
Intent Integrity Kit (IIKit) preserves your intent from idea to implementation through specification-driven development with cryptographic verification. Compatible with Claude Code, Codex, Gemini, OpenCode, and GitHub Copilot.
Intent Integrity Kit Workflow
This project uses specification-driven development. The phases are:
Utility: /iikit-core - Initialize project (git/GitHub setup, PRD seeding), uninit before tessl uninstall, check status, select active feature, show help (run init before starting)
Utility: /iikit-clarify - Resolve ambiguities in any artifact (spec, plan, checklist, testify, tasks, constitution) — runnable after any phase
Utility: /iikit-bugfix - Report and fix bugs without full specification workflow
/iikit-00-constitution- Define project governance principles/iikit-01-specify- Create feature specification from natural language/iikit-02-plan- Create technical implementation plan/iikit-03-checklist- Generate domain-specific quality checklists/iikit-04-testify- Generate test specifications (TDD support, optional unless constitutionally required)/iikit-05-tasks- Generate task breakdown/iikit-06-analyze- Validate cross-artifact consistency/iikit-07-implement- Execute implementation/iikit-08-taskstoissues- Export tasks to GitHub Issues
Never skip phases. Each /iikit-* command validates its prerequisites.
Read FRAMEWORK-PRINCIPLES.md for this framework's development principles.
Project Structure
.claude/skills/ # Development layout (source of truth)
iikit-core/ # Core skill with scripts and templates
scripts/bash/ # Bash scripts for all skills
scripts/powershell/ # PowerShell scripts for Windows
templates/ # Framework templates (do not edit)
references/ # Shared reference docs (do not edit)
iikit-00-constitution/ # Constitution skill
iikit-01-specify/ # Specification skill
... # Other iikit-XX-* skills
.codex/skills/ # Symlink -> .claude/skills
.gemini/skills/ # Symlink -> .claude/skills
.opencode/skills/ # Symlink -> .claude/skills
.github/copilot-instructions.md # Symlink -> AGENTS.md (GitHub Copilot)
CONSTITUTION.md # Project governance (content-agnostic, lives at root)
PREMISE.md # App-wide context: what, who, why, domain, scope
.specify/
context.json # Feature state between skill invocations
active-feature # Sticky active feature selection (survives restarts)
evals/ # Tessl eval results (fetched, not committed)
specs/ # Feature specifications (created per feature)
NNN-feature-name/
spec.md # Feature specification
plan.md # Implementation plan
tasks.md # Task breakdown
research.md # Research findings
data-model.md # Data model
quickstart.md # Quick start guide
contracts/ # API contracts
checklists/ # Quality checklists
tests/ # Test specifications (created by /iikit-04-testify)
features/ # Gherkin .feature files (locked by assertion hash)
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.
- 2d ago First seen · 168 lines · 1,874 tokens per session scan A d551b241dd3f
kit AGENTS.md is an instructions file published in the GitHub repository intent-integrity-chain/kit (47 stars, last pushed 2mo ago), licensed MIT. It adds 1,874 tokens to every session, about $0.0094 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.
Other instructions, from other repositories
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.