hope AGENTS.md

Project instructions for changing Hope, covering required documents, feature-specific guidance, writing standards, and completion checks.

In plain words
What is it for?
They guide work on Hope's implementation, shared code, dependencies, assets, features, GUI, documentation, and final review.
Why use it?
They tell contributors which project rules and design documents to read before making changes and how to verify the result.

Instructions file for CodexOpenCode

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/dkstm95/hope/agents-md
Clone the repo
git clone --depth 1 https://github.com/dkstm95/hope

Made for: Codex, OpenCode.

Per session 449 This file is loaded in full into every session.
When invoked 449 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 $0.00449 $0.00449
Opus 5 $0.00225 $0.00225
Sonnet 5 $0.00090 $0.00090
Haiku 4.5 $0.00045 $0.00045

Measured 2d ago against content hash 1ac76effd416, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hope 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI work instructions

Before changing Hope:

  • Read PRINCIPLES.md.
  • Follow the workflow in CONTRIBUTING.md.
  • Read docs/architecture.md before changing implementation dependencies, shared code or assets, a main folder, a build boundary, or delivery structure.
  • Read the matching plugins/hope/skills/<feature>/SKILL.md before changing feature behavior.
  • Read docs/design.md before changing a Hope GUI.

Writing

Use the Hope Write Skill whenever clearer language would improve the work.

Write applies the shared writing standard inside the active task.

When implementation or another Skill owns the task, Write remains cross-cutting. It does not create another workflow, worker, result, scope, or completion condition.

Completion

Before finishing, review the full changed scope against Prefer simple, direct design.

Remove support files, generation, packaging, documentation, and tests that no longer serve the remaining product.

Link to one authority instead of keeping parallel behavior descriptions unless another file owns a distinct contract or obligation.

Verify changed product behavior.

Skill discovery and manifest validity alone are not evidence that behavior works.

Run the relevant checks from CONTRIBUTING.md and report any remaining verification gap.

Before completing any file-changing task, follow the release decision and preparation steps in docs/release.md, then run npm run check.

Before committing or opening a pull request, choose one final title that follows the contribution rule. Validate it with npm run check:title -- "<title>", then use it for both the commit and pull request.

Do not finish while npm run check fails. Do not commit, open a pull request, or push while the selected title fails npm run check:title -- "<title>".

Read the full file on GitHub · 56 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 · 56 lines · 449 tokens per session scan A 1ac76effd416

Subscribe to this mod's changes

hope AGENTS.md is an instructions file published in the GitHub repository dkstm95/hope (8 stars, last pushed 3d ago), licensed MIT. It adds 449 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories