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 skills/reflexioai/claude-smart/ralphnpx skills add ReflexioAI/claude-smart --skill ralphgit clone --depth 1 https://github.com/ReflexioAI/claude-smartWhat 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 | $0.00064 | $0.01811 |
| Opus 5 | $0.00032 | $0.00905 |
| Sonnet 5 | $0.00013 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
ralph 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
97% identical to ralph — 13 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph PRD Converter
Converts existing PRDs to the prd.json format that Ralph uses for autonomous execution.
The Job
Take a PRD (markdown file or text) and convert it to prd.json in your ralph directory.
Output Format
{
"project": "[Project Name]",
"branchName": "ralph/[feature-name-kebab-case]",
"description": "[Feature description from PRD title/intro]",
"userStories": [
{
"id": "US-001",
"title": "[Story title]",
"description": "As a [user], I want [feature] so that [benefit]",
"acceptanceCriteria": [
"Criterion 1",
"Criterion 2",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
}
]
}
Story Size: The Number One Rule
Each story must be completable in ONE Ralph iteration (one context window).
Ralph spawns a fresh Amp instance per iteration with no memory of previous work. If a story is too big, the LLM runs out of context before finishing and produces broken code.
Right-sized stories:
- Add a database column and migration
- Add a UI component to an existing page
- Update a server action with new logic
- Add a filter dropdown to a list
Too big (split these):
- "Build the entire dashboard" - Split into: schema, queries, UI components, filters
- "Add authentication" - Split into: schema, middleware, login UI, session handling
- "Refactor the API" - Split into one story per endpoint or pattern
Rule of thumb: If you cannot describe the change in 2-3 sentences, it is too big.
Story Ordering: Dependencies First
Stories execute in priority order. Earlier stories must not depend on later ones.
Correct order:
- Schema/database changes (migrations)
- Server actions / backend logic
- UI components that use the backend
- Dashboard/summary views that aggregate data
Wrong order:
- UI component (depends on schema that does not exist yet)
- Schema change
Acceptance Criteria: Must Be Verifiable
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 · 258 lines · 64 tokens per session scan A 01e1742ab070
ralph is a skill published in the GitHub repository ReflexioAI/claude-smart (774 stars, last pushed 3d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,811 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to ralph, differing in 13 lines, and is treated as a copy.
Other skills, from other repositories
reflexio-embedded
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
reflexio-consolidate
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
reflexio
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
learn
When to use: The user wants immediate extraction of skills/preferences from the current session — e.g., after a major correction, before context compaction, or to test the loop.
clear-all
When to use: The user explicitly asks to delete all locally-stored skills/preferences. This is destructive and unrecoverable.
show
When to use: The user wants to see what reflexio currently knows about this project.