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/stagentic/stagentic-xdd/claude-mdgit clone --depth 1 https://github.com/stagentic/stagentic-xddWrote 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.
[](https://agentmods.dev/instructions/stagentic/stagentic-xdd/claude-md)<a href="https://agentmods.dev/instructions/stagentic/stagentic-xdd/claude-md"><img src="https://agentmods.dev/badge/instructions/stagentic/stagentic-xdd/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.03236 | $0.03236 |
| Opus 5 | $0.01618 | $0.01618 |
| Sonnet 5 | $0.00647 | $0.00647 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
stagentic-xdd CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stagentic-xdd
A planned Claude plugin for language-agnostic BDD/TDD ("XDD"). Initial focus is the inner loop (Red-Green-Refactor) for Python; the outer loop and additional language adapters are deferred.
See README.md for the framing and the link to the longer "what almost
everyone gets wrong about TDD/BDD" argument.
What to read when
Each line pairs a trigger — a task you're about to do, or a point in time — with what to read before you act on it. When a trigger applies, open the resource first; the line is a pointer, not a substitute for it.
- When starting a session, or a prompt is open-ended ("let's continue",
"what next?"): read
docs/working-practices.mdfirst. - When making or acting on an architectural decision: read the relevant ADR in
docs/architecture/decisions/first. Accepted ADRs must be adhered to; proposed ones are still under evaluation — possibly being implemented to assess them empirically. - When you need a developer command (test runner, linter, mutation): read
COMMANDS.mdfirst. - When writing any prose — commit, ADR, or doc body: read
docs/writing-style.mdfirst. - When proposing or writing a commit: read
docs/commit-style.mdfirst. - When editing an in-repo doc (README, ADR, CLAUDE.md): read
docs/document-style.mdfirst. - When writing a scenario, or otherwise using the
playframework: readplay/README.mdfirst. - When touching
play/tests/: readtest-conventions.mdfirst. - When touching
play/src/: readsrc-conventions.mdfirst, andplay/HOW_IT_WORKS.mdfor how the pieces fit together. - When touching
spec/: readspec-conventions.mdfirst. - When a real-agent run reveals a misstep: read
docs/lessons/TEMPLATE.mdfirst and record the lesson per ADR 0015.
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.
- 4d ago First seen · 214 lines · 3,236 tokens per session scan A 2e97f264d2a5
stagentic-xdd CLAUDE.md is an instructions file published in the GitHub repository stagentic/stagentic-xdd (5 stars, last pushed 10d ago), licensed MIT. It adds 3,236 tokens to every session, about $0.0162 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.
Other instructions, from other repositories
wallfacer CLAUDE.md
Instructions for changkun/wallfacer: If you didn't add a test, you didn't fix a bug. Every bug fix must include a reproducible test that fails without the fix and passes with it. You commit frequently, one small scope diff at a time. Push to main once a full batch of work is complete and verified. Leftover must be…
arc AGENTS.md
AGENTS.md instructions for howells/arc, covering arc, shape, gotchas, editing constraints and search order.
spec-driven-tdd AGENTS.md
Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.
engineering-skills CLAUDE.md
Claude Code instructions for int2t05/engineering-skills, covering claude.md, conventions and skill discovery.
mcp-repo-onboarding AGENTS.md
Instructions for rogermt/mcp-repo-onboarding, covering agents.md — agent & copilot instructions, current status, output verification, project identity and ⚠️ critical: tdd required.
speckit AGENTS.md
AGENTS.md instructions for jmanhype/speckit, covering agents.md - instructions for ai coding agents, core philosophy, pivotal methodology alignment, pivotal-style epic format and priority levels (pivotal-aligned).