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 ericrisco/rsc-harness --skill chatbotgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/chatbot)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/chatbot"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/chatbot/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/ericrisco/rsc-harness/chatbot"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/chatbot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 87 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Output Handling · line 146 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00078 | $0.03223 |
| Opus 5.5 | $0.00031 | $0.01289 |
| Sonnet 5.5 | $0.00016 | $0.00645 |
| Haiku 4.5 | $0.00008 | $0.00322 |
Grade A, and why
chatbot scanned grade A with 1 finding 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Injection defenses (full checklist in [`references/system-prompt-and-guardrails.md`](references/system-prompt-and-guardrails.md)): a clear instruction hierarchy (system > retrieved content > user), treat retrieved text a Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
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.
Ship the bot that lives on the website
This skill owns the bot that sits on a public site 24/7, answers support or sales questions, deflects what it safely can, and hands off cleanly what it can't. Four parts and nothing else: its persona (system prompt), its grounding (what it's allowed to know), its guardrails (what it must never say or do), and its handoff (when and how it gives up to a human). The retrieval engine under it is ../building-agents/SKILL.md; the human who picks up the escalation is ../customer-support/SKILL.md. You are productizing a bot, not engineering an agent and not working a ticket.
Not here: the agent loop, tool schemas and eval harness → ../building-agents/SKILL.md (and rag for the index half: chunking, embeddings, rerank); one live ticket answered by a human — triage, SLA, macros → ../customer-support/SKILL.md; prompt wording in the abstract → prompt-engineering; general LLM abuse taxonomy beyond the public-bot case → agent-safety; the golden-set eval as an engineering artifact → agent-eval; win-back/renewal → ../retention/SKILL.md; new-customer welcome → ../client-onboarding/SKILL.md; generic automation wiring → ../automation-flows/SKILL.md; WhatsApp/Telegram channel plumbing → ../whatsapp-telegram/SKILL.md.
The one rule
The bot may state only what it can cite (from approved KB) or confirm (a fact it was given). Everything else is "Let me connect you to a human." Grounded-or-handoff. It never improvises a price, a policy, a refund, or a promise.
Why: a hallucinated answer is a binding answer. Air Canada's bot invented a bereavement-refund policy; a tribunal held the airline liable for what the bot said (multiple 2025 retrospectives, accessed 2026-06-02). The bot speaks for the company in court, so cap what it's allowed to invent at zero.
What ships with it
5 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 · 78 tokens per session scan A c65d344a8211
chatbot is a skill published in the GitHub repository ericrisco/rsc-harness (231 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 3,223 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
safety-guardrails
Flags risky shell commands and unsafe tree ops.
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
setting-up-a-project
Use when asked to set up, onboard, initialize, or spec a project with no spec graph, or when invoked by the app's Set-up-project card. Not for ordinary work in an already-specced project.