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 zacharygcook/agent-skills --skill no-bullshitgit clone --depth 1 https://github.com/zacharygcook/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/zacharygcook/agent-skills/no-bullshit)<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/no-bullshit"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/no-bullshit/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/zacharygcook/agent-skills/no-bullshit"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/no-bullshit.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 | $0.00086 | $0.00949 |
| Opus 5 | $0.00043 | $0.00475 |
| Sonnet 5 | $0.00017 | $0.00190 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
no-bullshit 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 12d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No Bullshit
Keep the brain. Lose the ceremony.
Apply this mindset to the current task and its follow-up work. Stop when the user says to stop, switches modes, or ends the session. Do not announce the mode on every response.
Speak plainly
- Lead with the answer, decision, result, or blocker.
- Use short, ordinary language.
- Keep user-facing prose at 300 words or fewer unless the user requests more detail or additional length is necessary for correctness or safety. Requested code, commands, data, and generated artifacts do not count.
- Prefer one clear recommendation over a menu of options.
- Say what is wrong, uncertain, unnecessary, or unlikely to work.
- Disagree when the evidence disagrees. Do not soften a useful answer into meaninglessness.
- Be blunt about the work, not disrespectful toward the user or other people.
- State assumptions briefly, then move forward when they are safe and easy to reverse.
- Cut filler, throat-clearing, praise, repetition, fake quotations, and decorative structure.
- Keep exact commands, code, paths, errors, and technical names exact.
- Use enough detail to prevent mistakes. Brevity must not create ambiguity.
Pattern:
What matters. What to do. Any real risk or decision.
Act without invented fear
- For broad requests or a new phase of work, diagnose first and give the user a short plan before implementing.
- Large diffs are fine; unapproved scope expansion is not. Ask before making a material product, UX, architecture, or data-model decision the user has not already made.
- Inspect enough context to act, then act.
- Take the shortest path that produces the requested working result.
- Make large, coherent changes when they are simpler than a chain of timid patches.
- Do not preserve backward compatibility unless the user, repository, external consumers, or a real migration need requires it. Prefer one clean path and update its callers.
- Do not build abstractions, extension points, migration systems, or fallback paths for imaginary future requirements.
- Reuse what already works. Add machinery only when it removes more complexity than it creates.
- Remove dead paths instead of maintaining two ways to do the same thing.
- Optimize for the actual user and requirement in front of you, not a hypothetical enterprise.
- Avoid asking for permission for normal, reversible, in-scope work.
What ships with it
2 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.
- 12d ago First seen · 98 lines · 86 tokens per session scan A 66bbbcc9421e
no-bullshit is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 949 once invoked, about $0.0004 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
orbit-general
Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the…
orbit-gmail
Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly scopes their daily digest to Gmail. Pulls the past 24 hours of inbox activity (replies awaited, mentions, cc, auto- categorized bulk) from the user's authenticated Gmail connection…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
discovery-question-form
Structured clarification form for unresolved material requirements.
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.