tdder AGENTS.md

A set of instructions for working on Tdder, including where files belong, how to develop its agents on two platforms, and which project rules apply. TDD means test-driven development: writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it when discussing or changing Tdder, deciding which testing and project-maintenance guidance applies, or running its development workflow.
Why use it?
It requires the relevant project skills before changes, protects a read-only checkout, and prevents agents from publishing code or treating questions as requests to edit.

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/t1/tdder/agents-md
Clone the repo
git clone --depth 1 https://github.com/t1/tdder

Made for: Codex, OpenCode.

Per session 1,126 This file is loaded in full into every session.
When invoked 1,126 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 $0.01126 $0.01126
Opus 5 $0.00563 $0.00563
Sonnet 5 $0.00225 $0.00225
Haiku 4.5 $0.00113 $0.00113

Measured yesterday against content hash 12c6e3a0b607, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdder 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 yesterday.

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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Read README.md before starting any task — it has project overview, architecture, and conventions.

Before any code change, state which skills match (bug fixes and features → tdd, any work in this repo → project-hygiene) and read those skill files first. "Small fix" is not an exemption.

Do NOT read the TODO.md, unless instructed to.

VERY IMPORTANT Be very critical and honest to what I say. And when I ask a question, it's just a question, not a suggestion: don't start implementing, but start a discussion. Don't apologize for any mistakes, just tell me what went wrong and how we can stop it from happening again.

AND NEVER EVER PUBLISH ANYTHING — no git push, maven deploy, npm publish, or anything that sends code or artifacts to a remote. All that's the user's privilege!

File locations

~/.pi/agent/git/github.com/t1/tdder/ is a read-only checkout of this project — NEVER edit or commit there. The current working directory is the real repo. Always resolve skill file paths relative to CWD, not to the read-only checkout.

Claude Code vs pi

Claude Code agents cannot use tools provided by pi extensions (e.g. maven_run, maven_project_info, maven_lookup_version). They must use the equivalent tdder-maven CLI commands via bash instead. The skill files document both approaches.

Development

Most content is Markdown or JSON with no build step. However, some extensions/*/ subdirectories (e.g. maven/, unfolding/) are TypeScript projects with test suites — see their READMEs for details.

When doing TDD on any extension, load and follow the tdd skill.

Root dependency sections in package.json (dependencies, devDependencies, peerDependencies, optionalDependencies) are generated from the union of the same sections in extensions/*/package.json. There is currently no mechanism for manual root-only entries in those sections. After changing an extension dependency section, run npm run sync-root-deps and keep package-lock.json in sync.

Read the full file on GitHub · 102 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. yesterday First seen · 102 lines · 1,126 tokens per session scan A 12c6e3a0b607

Subscribe to this mod's changes

tdder AGENTS.md is an instructions file published in the GitHub repository t1/tdder (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,126 tokens to every session, about $0.0056 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.