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 skills add 2ykwang/agent-skills --skill ralph-loop-templategit clone --depth 1 https://github.com/2ykwang/agent-skillsWrote 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/skills/2ykwang/agent-skills/ralph-loop-template)<a href="https://agentmods.dev/skills/2ykwang/agent-skills/ralph-loop-template"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/ralph-loop-template/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/2ykwang/agent-skills/ralph-loop-template"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/ralph-loop-template.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.01508 |
| Opus 5.5 | $0.00014 | $0.00603 |
| Sonnet 5.5 | $0.00007 | $0.00302 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
ralph-loop-template 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 1mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Loop Template
Input
$ARGUMENTS
Instructions
Step 1: Gather Plan
If an argument is provided: Read the file to understand the plan content.
If no argument: Search for a plan in the following order:
- Search for plan files in the project root:
PLAN.md,plan.md,PLAN-*.md,plan-*.md,TODO.md,prd.md,PRD.md- 1 found → Use it (inform the user which file was detected)
- Multiple found → Present the list and ask for selection
- 0 found → Proceed to next step
- Use the plan discussed in the current conversation context.
- If no plan exists in the conversation context, ask the user to describe the plan.
Step 2: Identify Project Environment
Collect project-specific information to embed in the PROMPT file.
Search for agent/project configuration files in the following priority order:
CLAUDE.md(Claude Code).cursorrules(Cursor).windsurfrules(Windsurf)AGENTS.md,COPILOT.md,GEMINI.md
If a config file is found, extract:
- Verification commands: Combine build, test, lint into a single chain (e.g.,
npm run lint && npm run build && npm test) - Key code style rules (items to insert into the PROMPT's absolute rules
{AGENT_RULES}, max 3)
If no config file is found: Infer from project structure:
package.json→ npm/yarn commandsMakefile/Justfile→ make/just commandsCargo.toml→ cargo commandspyproject.toml/setup.py→ python toolchain- If undetectable, ask the user for build/test commands
Step 3: Analyze Plan
Extract the following from the plan:
- Goal: What is being built
- Non-goals: What will NOT be done in this task (to prevent Feature Invention)
- Phase list: Ordered implementation steps
- Key content per phase: Files to change, implementation details
- Reference docs/files: Pattern references, design document paths
- Completion criteria: Criteria for determining the entire task is complete
Completion criteria must be mechanically verifiable (e.g., command execution returns exit code 0). Do not use subjective criteria like "works well" or "looks clean".
What ships with it
4 files 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.
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.
- 1mo ago First seen · 152 lines · 36 tokens per session scan A 8bdd489397af
ralph-loop-template is a skill published in the GitHub repository 2ykwang/agent-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,508 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
resolve-plugins
Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
agents-md
Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.
api-rate-limit-handler
Implement bounded, idempotency-aware API throttling, backoff, and retry handling for 429 and transient 5xx responses.
api-endpoint-builder
Builds production-ready REST API endpoints with validation, error handling, authentication, and documentation. Follows best practices for security and scalability.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.