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/codecast-sh/codecast/helpgit clone --depth 1 https://github.com/codecast-sh/codecastWhat 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 | $0.00007 | $0.00768 |
| Opus 5 | $0.00003 | $0.00384 |
| Sonnet 5 | $0.00001 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
help 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.
This is a copy
88% identical to help — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Loop Plugin Help
Please explain the following to the user:
What is Ralph Loop?
Ralph Loop implements the Ralph Wiggum technique - an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley.
Core concept:
while :; do
cat PROMPT.md | claude-code --continue
done
The same prompt is fed to Claude repeatedly. The "self-referential" aspect comes from Claude seeing its own previous work in the files and git history, not from feeding output back as input.
Each iteration:
- Claude receives the SAME prompt
- Works on the task, modifying files
- Tries to exit
- Stop hook intercepts and feeds the same prompt again
- Claude sees its previous work in the files
- Iteratively improves until completion
The technique is described as "deterministically bad in an undeterministic world" - failures are predictable, enabling systematic improvement through prompt tuning.
Available Commands
/ralph-loop [OPTIONS]
Start a Ralph loop in your current session.
Usage:
/ralph-loop "Refactor the cache layer" --max-iterations 20
/ralph-loop "Add tests" --completion-promise "TESTS COMPLETE"
Options:
--max-iterations <n>- Max iterations before auto-stop--completion-promise <text>- Promise phrase to signal completion
How it works:
- Creates
.claude/.ralph-loop.local.mdstate file - You work on the task
- When you try to exit, stop hook intercepts
- Same prompt fed back
- You see your previous work
- Continues until promise detected or max iterations
/cancel-ralph
Cancel an active Ralph loop (removes the loop state file).
Usage:
/cancel-ralph
How it works:
- Checks for active loop state file
- Removes
.claude/.ralph-loop.local.md - Reports cancellation with iteration count
Key Concepts
Completion Promises
To signal completion, Claude must output a <promise> tag:
<promise>TASK COMPLETE</promise>
The stop hook looks for this specific tag. Without it (or --max-iterations), Ralph runs infinitely.
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 · 127 lines · 7 tokens per session scan A 51bbd57d6edf
help is a command published in the GitHub repository codecast-sh/codecast (30 stars, last pushed yesterday), licensed MIT. It adds 7 tokens to every session and 768 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to help, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
dev
TDD Developer agent - implements features using test-driven development and clean code principles.
implement
E2E-first Test driven development — unit tests written last.
research
Assess a new agent's hook/lifecycle compatibility with the Entire CLI.
t800-doctor
Зачем: быстрый scripts-only отчёт: версия, profile, memory, STATE, counts, alwaysApply, последние audits — без narrative-агента по умолчанию.
t800-onboard
Для чата с новичками. Показывает, что настроено в Cursor (global + local), и что умеет отдел T-800.
t800-bootstrap
Запускайте один раз при установке плагина или для новичка в чате.