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/t1/tdder/agents-mdgit clone --depth 1 https://github.com/t1/tdderWhat 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 | $0.01126 | $0.01126 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
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.
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.
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.
- yesterday First seen · 102 lines · 1,126 tokens per session scan A 12c6e3a0b607
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.
Other instructions, from other repositories
nuxt-supabase-starter CLAUDE.md
Instructions for YuDefine/nuxt-supabase-starter, covering claude.md, language, project structure and meta vs template 邊界.
arc AGENTS.md
Instructions for howells/arc, covering arc, shape, gotchas, editing constraints and search order.
gem-team AGENTS.md
Instructions for mubaidr/gem-team, covering agents.md, project overview, key features, setup commands and install apm (agent package manager).
specs-driven-development-spring-angular always-on.instructions.md
Always-on guardrails for spec-driven Spring + Angular development.
clean-code-skills clean-code.instructions.md
Instructions for btseee/clean-code-skills, covering clean-code instructions, clean code rules (clean-code-skills), work loop, dependency direction and file and code placement.
specs-driven-development-spring-angular production-code.instructions.md
Production code guardrails — TDD discipline and Spring Boot 4 conventions.