agentmods.dev

hodor: Instructions file for Codex

AGENTS.md

hodor AGENTS.md is an instructions file for Codex, OpenCode from mr-karan/hodor. It costs 1,764 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for the hodor repository, covering organization, setup, the pi-coding-agent SDK, and pull-request review.

In plain words
What is it for?
Use it when developing in hodor, setting up the workspace, understanding its SDK architecture, or reviewing a pull request.
Why use it?
It gives a coding agent the repository rules and structure it needs before making or reviewing changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mr-karan/hodor's own configuration. It tells Codex and OpenCode how to work on hodor itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hodor configures →

not rated 112repo changed 29d ago A scan 1,764 tokens original MIT
View source ↗ mr-karan/hodor
Reuse

Borrowing it

Nothing to install: this file belongs to mr-karan/hodor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mr-karan/hodor/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mr-karan/hodor

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for hodor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mr-karan/hodor/agents-md/github.svg)](https://agentmods.dev/instructions/mr-karan/hodor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mr-karan/hodor/agents-md"><img src="https://agentmods.dev/badge/instructions/mr-karan/hodor/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hodor AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mr-karan/hodor/agents-md"><img src="https://agentmods.dev/badge/instructions/mr-karan/hodor/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,764 This file is loaded in full into every session.
When invoked 1,764 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01764 $0.01764
Opus 5.5 $0.00706 $0.00706
Sonnet 5.5 $0.00353 $0.00353
Haiku 4.5 $0.00176 $0.00176

Measured 29d ago against content hash d8747258b934, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hodor 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 29d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Hodor is an AI code reviewer for GitHub PRs, GitLab MRs, Gitea/Forgejo PRs, and local diffs. It is TypeScript, built with tsup, runs on Bun (Node 22 compatible), and uses the Pi coding-agent SDK (@earendil-works/pi-coding-agent, @earendil-works/pi-ai) as its agent runtime. The primary deployment is GitLab CI through a shared template.

Project map

The full module table is in README.md under Architecture. The paths you touch most:

  • src/agent.ts: review orchestration. Preflight, workspace, Pi session, the submit_review tool, recovery, metrics.
  • src/model.ts, src/models-json.ts: model strings, Bedrock ARN models, adaptive reasoning, HODOR_MODELS_JSON.
  • src/review-diff.ts: full, incremental, and snapshot diff bases.
  • src/publisher.ts, src/gitlab.ts: GitLab inline notes, a new summary note per review (older summaries collapsed to a link), and verified-fix replies on finding threads.
  • src/resolve-location.ts: snippet-based line resolution.
  • templates/: default review profile and review task prompt.
  • tests/: vitest, *.test.ts.

Pi SDK integration

  • Session: createAgentSession() with tools git_diff, read, grep, find, ls, and submit_review (terminate: true). All but submit_review come from src/review-tools.ts: git_diff serves the precomputed diff, and the others replace Pi's built-ins with versions confined to git ls-files. There is no bash. --tiny-diff-fast-path exposes only submit_review.
  • Models: createModelRuntime() in src/models-json.ts wraps ModelRuntime.create(). Registry models come from modelRuntime.getModel(). Bedrock application inference profile ARNs are built by buildBedrockArnModel() from an @<base-model-id> registry entry.
  • Settings: SettingsManager.inMemory() enables compaction, sets cacheWarming: "off" (Pi defaults to streaming warming, which costs money in one-shot CI), and bounds retries (retry.maxAgentDelayMs).
  • Bedrock request fields: wrapBedrockStream() wraps session.agent.streamFunction to add requestMetadata and OpenAI-on-Bedrock reasoning. The instance property is streamFunction; streamFn is only the constructor option.
  • Errors: the SDK stores failed turns in session.state.errorMessage. Check it after session.prompt().
  • Metrics: read usage from session.getSessionStats(). session.messages is the projected context and omits compacted and retried turns.
  • Events: session.subscribe() drives verbose progress, including auto_retry_* and compaction_* events.

Read the full file on GitHub · 85 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. 29d ago Changed · +1 lines · +93 tokens per session d8747258b934
  2. 1mo ago Changed · +9 lines · +568 tokens per session aaeacf01467d
  3. 2mo ago First seen · 75 lines · 1,103 tokens per session scan A 1d5f7eae3b18

Subscribe to this mod's changes

hodor AGENTS.md is an instructions file published in the GitHub repository mr-karan/hodor (112 stars, last pushed 22d ago), licensed MIT. It adds 1,764 tokens to every session, about $0.0071 per session on Opus 5.5. 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.

CI and CDCode reviewPlanningagentaicode-qualitydeveloper-tools
Related

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens