agentmods.dev

Grape AGENTS.md

Project-specific instructions for coding agents working on Grape. They define which design documents to read, how to handle missing specifications, and what checks are required before editing or adding code.

In plain words
What is it for?
Use them when changing Grape to navigate its documentation, validate design decisions, keep files modular, and run the appropriate typechecking and test gates.
Why use it?
They reduce the risk of implementing behavior that conflicts with Grape's documented architecture, contracts, or development stage.

Instructions file for CodexOpenCode

11 1mo ago A scan 2,431 tokens original MIT
View the source file gael55x/Grape
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/gael55x/grape/agents-md
Clone the repo
git clone --depth 1 https://github.com/gael55x/Grape

Made for: Codex, OpenCode.

Per session 2,431 This file is loaded in full into every session.
When invoked 2,431 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 $0.02431 $0.02431
Opus 5 $0.01215 $0.01215
Sonnet 5 $0.00486 $0.00486
Haiku 4.5 $0.00243 $0.00243

Measured 2d ago against content hash 5bac3076ac01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Grape 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 · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Operating Rules

These rules apply to AI coding agents working on Grape.

Before Editing

Read these files first:

  1. docs/v1/README.md
  2. docs/v1/SPEC.md
  3. docs/v1/architecture/invariants.md
  4. docs/v1/architecture/state-machine.md
  5. docs/v1/planning/implementation-roadmap.md
  6. The specific domain doc for the module you will edit

If the needed behavior is not documented, update the docs before or with the implementation.

Do not implement from placeholders. If a supporting doc says what it should contain but does not define the contract, read docs/v1/SPEC.md and harden the supporting doc first.

Before adding code to an existing large file, read docs/v1/architecture/overview.md#code-modularity-standards. If the file is past the split checkpoint, split by ownership before adding another responsibility.

The current in-memory smoke harness is not a substitute for typechecking or behavioral tests. After the In-Memory Context Loop, do not add broad feature code until Project Skeleton And Tooling wires real TypeScript and test gates.

Documentation Traversal

Use docs/README.md for the top-level map and docs/v1/README.md for V1 work.

For V1 implementation, start with docs/v1/SPEC.md, then read only the folder that owns the change:

  • docs/v1/architecture/ for system shape, state machine, and invariants.
  • docs/v1/core/ for trust, compression, storage, and security.
  • docs/v1/contracts/ for context artifact and context diff schemas.
  • docs/v1/interfaces/ for MCP and CLI contracts.
  • docs/v1/quality/ for tests and benchmarks.
  • docs/v1/planning/ for roadmap, logs, and changelogs.
  • docs/v1/decisions/ for accepted ADRs.
  • docs/v1/examples/ and docs/v1/fixtures/ for serialized examples and fixture expectations.
  • docs/v1/legacy/alpha/ for historical alpha-era documentation only. Do not treat legacy docs as current implementation input.

Do not add new V1 topic files directly under docs/v1/ unless they are canonical anchors like README.md or SPEC.md.

Read the full file on GitHub · 169 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 · 169 lines · 2,431 tokens per session scan A 5bac3076ac01

Subscribe to this mod's changes

Grape AGENTS.md is an instructions file published in the GitHub repository gael55x/Grape (11 stars, last pushed 1mo ago), licensed MIT. It adds 2,431 tokens to every session, about $0.0122 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.

Data and AIGit and workflowTestingai-agentsclicoding-agentscontext-engineeringdeveloper-toolslocal-first
Related

Other instructions, from other repositories

open-design AGENTS.md

AGENTS.md instructions for nexu-io/open-design, covering directory guide, core documentation index, workspace directories, inactive or placeholder directories and development workflow.

nexu-io/open-design · 10,311 tokens

repoprompt-ce AGENTS.md

Instructions for repoprompt/repoprompt-ce, covering agent notes, contribution preflight, run, debug and uncoordinated equivalents.

repoprompt/repoprompt-ce · 4,478 tokens

ORG2 AGENTS.md

AGENTS.md instructions for org2AI/ORG2, covering agents.md — agent skill routing for orgii, skill routing table, root-cause-first bug fixing, default delivery flow and ui copy conventions.

org2AI/ORG2 · 3,019 tokens

flameox AGENTS.md

Instructions for morluto/flameox, covering repository guidelines, product direction, project structure & module organization, build, test, and development commands and coding style & naming conventions.

morluto/flameox · 1,170 tokens

awesome-loop-engineering AGENTS.md

Instructions for ChaoYue0307/awesome-loop-engineering, covering repository guidance for ai agents, scope, editing rules, commit identity rule and entry format.

ChaoYue0307/awesome-loop-engineering · 611 tokens

x-harness AGENTS.md

Instructions for BrianNguyen29/x-harness, covering x-harness agent contract, canonical tiers, completion rule, verifier rule and pgv rule.

BrianNguyen29/x-harness · 1,864 tokens