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 commands/aegntic/compound-engineering/ralph-loopgit clone --depth 1 https://github.com/aegntic/compound-engineeringWhat 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 | $0.00019 | $0.00319 |
| Opus 5 | $0.00010 | $0.00160 |
| Sonnet 5 | $0.00004 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
ralph-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ralph Loop
Start a self-referential loop using the stop hook mechanism.
Ralph is the canonical red-green-refactor engine behind /workflows:work when the resolved TDD contract selects Ralph-driven execution. Use this command directly only when you need manual control outside the orchestrated work path; it is not a detached alternative workflow.
Setup
Run the setup script via Bash tool:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh" $ARGUMENTS
After setup, proceed with the prompt specified in the arguments. The stop hook will prevent exit and feed the prompt back until the completion promise is output or max iterations are reached.
Any Ralph-driven run should preserve this contract:
- RED first -- run failing tests before implementation
- GREEN second -- add the minimal implementation needed to pass
- REFACTOR third -- clean up behavior-preserving code
- POST-REFACTOR RERUN -- rerun the required tests and capture stable report evidence for:
RedGreenPost-Refactor Green
To signal completion, output: <promise>YOUR_PROMISE_TEXT</promise>
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.
- 2d ago First seen · 37 lines · 19 tokens per session scan A 9e5b33bdd622
ralph-loop is a command published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 319 once invoked, about $0.0001 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 commands, from other repositories
kotlin-test
Enforce TDD workflow for Kotlin. Write Kotest tests first, then implement. Verify 80%+ coverage with Kover.
cpp-test
Enforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.
go-test
Enforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.
tdd-requirements
TDD開発の要件整理を行います。機能要件を明確化し、テスト駆動開発のための準備を行います。.
go-test
Go TDD workflow with table-driven tests.
cli-anything-web:refine
Refine an existing cli-anything-web CLI by recording additional traffic and expanding command coverage. Invokes the gap-analyzer skill as its first step, then implements missing endpoints.