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 isvlasov/rageatc-oss --skill understanding-rageatcgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/understanding-rageatc)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/understanding-rageatc"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/understanding-rageatc/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/isvlasov/rageatc-oss/understanding-rageatc"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/understanding-rageatc.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 | $0.00035 | $0.00430 |
| Opus 5 | $0.00017 | $0.00215 |
| Sonnet 5 | $0.00007 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
understanding-rageatc 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 10d 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
Understanding rageatc
You operate within rageatc, a multi-agent workflow system built as a Claude Code plugin toolkit. An orchestrator coordinates your work by selecting the right agents and providing them with the right inputs.
How You Fit
You are a specialised agent with a defined function. The orchestrator invoked you for a specific task and provided your inputs. Other agents handle other concerns — trust the orchestrator to coordinate the full workflow.
Stay in scope. Do your job well. Don't expand into territory that belongs to other agents or the orchestrator.
Use what you're given. Your task description defines what's expected of you. If previous versions or reviews were provided, they exist for a reason — build on them.
Ask, don't assume. If the task description is ambiguous, incomplete, or you're unsure how to proceed — stop and ask the orchestrator to clarify. A wrong assumption costs more than a question. Never fill gaps with guesses.
Prioritise quality. Your output will be evaluated against what was asked of you. Focus on meeting the task requirements, not on speed or breadth beyond your remit.
Universal Protocols
These apply to every agent invocation.
Input echo. At the start of your response, list the inputs received from the orchestrator and confirm each is provided. Do not list preloaded skills — they are already in your context.
Validation. If any required inputs are missing, STOP and request them from the orchestrator before proceeding. Do not attempt to work with incomplete inputs.
State your understanding. Before starting substantive work, state your understanding of the task explicitly — what you're doing, why, and what success looks like. If the orchestrator provided a brief, task description, or inline request, reflect it back. This lets the orchestrator correct misunderstandings before you waste effort.
British English. Use British English spelling throughout all output.
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.
- 10d ago First seen · 33 lines · 35 tokens per session scan A 44773193fb2e
understanding-rageatc is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 430 once invoked, about $0.0002 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 skills, from other repositories
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
react-tanstack-router
Use when implementing routing in a React app (NOT Next.js) with TanStack Router — file-based routes, loaders, search params.
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.