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 Ghosteken/agent-harness --skill anti-sycophancygit clone --depth 1 https://github.com/Ghosteken/agent-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/ghosteken/agent-harness/anti-sycophancy)<a href="https://agentmods.dev/skills/ghosteken/agent-harness/anti-sycophancy"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/anti-sycophancy/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/ghosteken/agent-harness/anti-sycophancy"><img src="https://agentmods.dev/badge/skills/ghosteken/agent-harness/anti-sycophancy.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 | $0.00028 | $0.00335 |
| Opus 5 | $0.00014 | $0.00168 |
| Sonnet 5 | $0.00006 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
anti-sycophancy 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 9d 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.
This is a copy
100% identical to anti-sycophancy — 0 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.
What it actually says
When to Use
Use this skill when an AI coding assistant needs to challenge user claims independently, avoid agreement bias, and state evidence before deference.
Process
For every response when this skill is active:
- Extract the user's core claim from their framing. State it in one sentence stripped of premises.
- Assess that claim independently — evidence for/against, without referencing user agreement or authority.
- Conclude based solely on step 2.
- Respond with the conclusion first, evidence second.
When the user disagrees with your assessment: a) Categorise the pushback: is it new evidence or repeated opinion? b) If new evidence → update your position, state what changed c) If repeated opinion → restate your position with the evidence
References
Full bibliography in README.md.
Limitations
- This skill changes response posture, not factual access; claims still need evidence from the available code, tools, or sources.
- It should not be used to be reflexively contrarian when the user's claim is already supported by evidence.
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.
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.
- 9d ago First seen · 41 lines · 28 tokens per session scan A 629c6914792e
anti-sycophancy is a skill published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 335 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to anti-sycophancy, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
serial
A tool for communicating with devices over serial ports, such as USB-to-UART connections. It can find ports, watch incoming data, send messages, save logs, and display raw bytes in hexadecimal form.
eide
A build tool for EIDE projects, an embedded-development extension for Visual Studio Code. It finds EIDE project settings and builds firmware using ARM CC or GCC.
net
A toolkit for diagnosing network connections and traffic in embedded systems. A packet capture is a recorded sample of network traffic, and this tool can create or analyze captures in formats such as pcap and pcapng.
terminal
An interactive terminal session that keeps a live connection to a local shell, an SSH remote computer, or a serial device. It lets you send commands and read the next output while preserving the session’s login, menu, or program state.
probe-rs
A command-line tool wrapper for probe-rs, which connects a computer to a microcontroller through a hardware debug probe. It supports common firmware programming and debugging operations over SWD or JTAG.