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 summarybotng/summarybot-ng --skill brutal-honesty-reviewgit clone --depth 1 https://github.com/summarybotng/summarybot-ngWrote 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/summarybotng/summarybot-ng/brutal-honesty-review)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/brutal-honesty-review"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/brutal-honesty-review/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/summarybotng/summarybot-ng/brutal-honesty-review"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/brutal-honesty-review.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 | $0.00072 | $0.01822 |
| Opus 5 | $0.00036 | $0.00911 |
| Sonnet 5 | $0.00014 | $0.00364 |
| Haiku 4.5 | $0.00007 | $0.00182 |
Grade A, and why
brutal-honesty-review 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 7d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brutal Honesty Review
<default_to_action> When brutal honesty is needed:
- CHOOSE MODE: Linus (technical), Ramsay (standards), Bach (BS detection)
- VERIFY CONTEXT: Senior engineer? Repeated mistake? Critical bug? Explicit request?
- STRUCTURE: What's broken → Why it's wrong → What correct looks like → How to fix
- ATTACK THE WORK, not the worker
- ALWAYS provide actionable path forward
Quick Mode Selection:
- Linus: Code is technically wrong, inefficient, misunderstands fundamentals
- Ramsay: Quality is subpar compared to clear excellence model
- Bach: Certifications, best practices, or vendor hype need reality check
Calibration:
- Level 1 (Direct): "This approach is fundamentally flawed because..."
- Level 2 (Harsh): "We've discussed this three times. Why is it back?"
- Level 3 (Brutal): "This is negligent. You're exposing user data because..."
DO NOT USE FOR: Junior devs' first PRs, demoralized teams, public forums, low psychological safety
Minimum Findings Enforcement
All brutal honesty reviews enforce a minimum of 3 weighted findings (CRITICAL=3, HIGH=2, MEDIUM=1, LOW=0.5). If the initial review finds fewer, escalate to deeper analysis. Brutally honest reviewers should ALWAYS find something -- if you can't, explain exactly why with evidence. </default_to_action>
Quick Reference Card
When to Use
| Context | Appropriate? | Why |
|---|---|---|
| Senior engineer code review | ✅ Yes | Can handle directness, respects precision |
| Repeated architectural mistakes | ✅ Yes | Gentle approaches failed |
| Security vulnerabilities | ✅ Yes | Stakes too high for sugar-coating |
| Evaluating vendor claims | ✅ Yes | BS detection prevents expensive mistakes |
| Junior dev's first PR | ❌ No | Use constructive mentoring |
| Demoralized team | ❌ No | Will break, not motivate |
| Public forum | ❌ No | Public humiliation destroys trust |
Three Modes
| Mode | When | Example Output |
|---|---|---|
| Linus | Code technically wrong | "You're holding the lock for the entire I/O. Did you test under load?" |
| Ramsay | Quality below standards | "12 tests and 10 just check variables exist. Where's the business logic?" |
| Bach | BS detection needed | "This cert tests memorization, not bug-finding. Who actually benefits?" |
What ships with it
7 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.
- 7d ago First seen · 244 lines · 72 tokens per session scan A 4ee1b2274d63
brutal-honesty-review is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,822 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 2026-09-03.
Other skills, from other repositories
brutal-honesty-review
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
code-quality
Análise proativa e sob demanda de qualidade de código. Detecta código morto, duplicações, oportunidades de consolidação, complexidade excessiva e code smells. Sugere melhorias e executa correções com aprovação. Triggers on: código morto, dead code, duplicação, duplicated, cleanup, refactor, complexidade, smell…
code-quality-engineer
Consolidated code quality skill combining debugging, code review, and QA testing. Provides systematic root-cause analysis, architecture conformance checks, test strategy, and bug reporting. Ensures every feature meets quality bar. Combines: debugger + code-reviewer + qa-engineer.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…