ralph

A queue-processing workflow that handles tasks in fresh isolated phases by assigning each task to a separate subagent. It supports serial, parallel, filtered, and dry-run processing.

In plain words
What is it for?
Use it to process a chosen number of pipeline tasks, optionally filter by batch or phase, run tasks concurrently, preview the work, or produce a structured handoff.
Why use it?
Fresh context reduces the chance that earlier tasks affect later ones and keeps each phase focused on its own work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agenticnotetaking/arscontexta/ralph
Any agent
npx skills add agenticnotetaking/arscontexta --skill ralph
Clone the repo
git clone --depth 1 https://github.com/agenticnotetaking/arscontexta

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.05168
Opus 5 $0.00030 $0.02584
Sonnet 5 $0.00012 $0.01034
Haiku 4.5 $0.00006 $0.00517

Measured yesterday against content hash 7b4ee932f92d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skill-sources/ralph/SKILL.md · 603 lines

How it starts

The opening of the file, as written. The whole thing — 603 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXECUTE NOW

Target: $ARGUMENTS

Parse arguments:

  • N (required unless --dry-run): number of tasks to process
  • --parallel: concurrent claim workers (max 5) + cross-connect validation
  • --batch [id]: process only tasks from specific batch
  • --type [type]: process only tasks at a specific phase (extract, create, reflect, reweave, verify, enrich)
  • --dry-run: show what would execute without running
  • --handoff: output structured RALPH HANDOFF block at end (for pipeline chaining)

Step 0: Read Vocabulary

Read ops/derivation-manifest.md (or fall back to ops/derivation.md) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.

START NOW. Process queue tasks.


MANDATORY CONSTRAINT: SUBAGENT SPAWNING IS NOT OPTIONAL

You MUST use the Task tool to spawn a subagent for EVERY task. No exceptions.

This is not a suggestion. This is not an optimization you can skip for "simple" tasks. The entire architecture depends on fresh context isolation per phase. Executing tasks inline in the lead session:

  • Contaminates context (later tasks run on degraded attention)
  • Skips the handoff protocol (learnings are not captured)
  • Violates the ralph pattern (one phase per context window)

If you catch yourself about to execute a task directly instead of spawning a subagent, STOP. Call the Task tool. Every time. For every task. Including create tasks. Including "simple" tasks.

The lead session's ONLY job is: read queue, spawn subagent, evaluate return, update queue, repeat.


Phase Configuration

Each phase maps to specific Task tool parameters. Use these EXACTLY when spawning subagents.

Phase Skill Invoked Purpose
extract /reduce Extract claims from source material
create (inline note creation) Write the {DOMAIN:note} file
enrich /enrich Add content to existing {DOMAIN:note}
reflect /reflect Find connections, update {DOMAIN:topic map}s
reweave /reweave Update older {DOMAIN:note_plural} with new connections
verify /verify Description quality + schema + health checks

Read the full file on GitHub · 603 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 603 lines · 61 tokens per session scan A 7b4ee932f92d

Subscribe to this mod's changes

ralph is a skill published in the GitHub repository agenticnotetaking/arscontexta (3,483 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 5,168 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

dogfood

Run a dogfooding session for hyalo — build from source, exercise the CLI against real knowledgebases (own KB, MDN, GitHub Docs, VS Code docs), find bugs, verify recent fixes, assess UX, measure performance, and write a structured report. Use this skill whenever the user says /dogfood, "dogfood", "run a dogfood…

ractive/hyalo · 102 tokens

release

Cut a hyalo release end-to-end — verify/bump the workspace version, rotate the changelog with hyalo itself, sync the winget fork, publish the GitHub release with curated + auto-generated notes, and watch the pipeline. Use this skill whenever the user wants to release a new hyalo version, cut/tag/publish vX.Y.Z, says…

ractive/hyalo · 102 tokens

review-rust

Perform critical Rust code reviews covering correctness, edition 2024 compliance, error handling, API design, async pitfalls, and dependency hygiene. ALWAYS use this skill when the user wants to review, audit, or critically evaluate Rust code — whether that's a PR diff, a specific crate or module, a cross-cutting…

ractive/hyalo · 177 tokens

security-audit

REQUIRED skill for any security-related request. Use this skill whenever the user wants to find anything dangerous, sensitive, or risky in their code, files, or repository. This includes but is not limited to: scanning for secrets/keys/tokens/credentials, checking dependencies for vulnerabilities, auditing destructive…

ractive/hyalo · 150 tokens

hyalo-tidy

../../../crates/hyalo-cli/templates/skill-hyalo-tidy.md.

ractive/hyalo · 0 tokens

hyalo

../../../crates/hyalo-cli/templates/skill-hyalo.md.

ractive/hyalo · 0 tokens