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/romyhaik/gim/agents-mdgit clone --depth 1 https://github.com/RomyHaik/gimWrote 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.
[](https://agentmods.dev/instructions/romyhaik/gim/agents-md)<a href="https://agentmods.dev/instructions/romyhaik/gim/agents-md"><img src="https://agentmods.dev/badge/instructions/romyhaik/gim/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01766 | $0.01766 |
| Opus 5 | $0.00883 | $0.00883 |
| Sonnet 5 | $0.00353 | $0.00353 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
gim 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GIM Framework — Agent Instructions
This repository contains the GIM (Goal-in-Mind) Framework.
Project structure
src/core/— Core engine, markdown I/O, parser, types, utils, passive evaluator, budget estimatorsrc/commands/— CLI commands: init, goal, check, focus, mode, prompt, validate, brainstorm, scope, resolve, task, context, graph, install, exportsrc/cli/— CLI entry point (commander-based)hook-templates/— zero-dep Node hook scripts copied into a project bygim install claude-code(PreToolUse sync between Claude Code and GIM)schemas/gim/— GIM schema definition (YAML) and templatesbin/gim.js— CLI binary entry pointdist/— built output, committed and shipped (see "Distribution" below)
Key abstractions
- GIM (
gim-engine.ts) — Main engine. Orchestrates checks, manages state, learning loop, task management. - PassiveEvaluator (
passive-evaluator.ts) — The single unified evaluator behindgim checkand task auto-check. Runs four checks (alignment, necessity, clarity, intent) in precedence order and dispatches to four issue types (drift, overbuild, ambiguity, intent-mismatch). Boundary matches and learned rules short-circuit the loop. Replaced the earlierScopeGuard+IntentAnalyzersplit in v0.4. - BudgetEstimator (
budget-estimator.ts) — Computes a soft per-task token budget at task-creation time from goal-relevance × mode × confidence × complexity. Produces arationalestring explaining which signals pushed the estimate which way. Overridable viagim task add --budget N. - GoalTracker (
goal-tracker.ts) — Relevance scoring with concept expansion. Used by the evaluator and estimator. - ModeManager (
mode-manager.ts) — Operational modes and mode change suggestions. - Markdown I/O (
markdown-io.ts) — Reads/writes the.gim/vault. Each GIM artifact is a markdown file with YAML frontmatter and wiki-link edges. Handles backward-compatible migration of legacy check-type names on read. - Markdown Parser (
markdown-parser.ts) — Frontmatter parsing, serialization, wiki-link extraction. - Validator (
validator.ts) — Rates idea alignment 1-5, boundary-aware. (Used bygim validate.) - Brainstormer (
brainstormer.ts) — Finds connections between ideas and the goal. (Used bygim brainstorm.) - PromptGenerator (
prompt-generator.ts) — System prompts with reason layers + non-goals/out-of-scope for AI tools (used bygim prompt).
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.
- 3d ago First seen · 81 lines · 1,766 tokens per session scan A 5ab859040b67
gim AGENTS.md is an instructions file published in the GitHub repository RomyHaik/gim (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,766 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
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).
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.
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.
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.
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).
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.