unslop-answers

unslop-answers is a skill for Claude Code from jaktestowac/awesome-copilot-for-testers. It costs 151 tokens per session (3,709 once invoked), scanned A, original, MIT.

A review guide for making an agent's answers about its work factual and evidence-based. It flags unsupported claims, invented details, and unclear numbers.

In plain words
What is it for?
It helps check bug reports, review findings, test results, release recommendations, file references, and quoted metrics.
Why use it?
It helps prevent people from trusting statements such as “the tests pass” when no test was run or “nothing else uses this” when the search was incomplete.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Good fit It helps check bug reports, review findings, test results, release recommendations, file references, and quoted metrics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jaktestowac/awesome-copilot-for-testers/unslop-answers
Install

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.

Any agent
npx skills add jaktestowac/awesome-copilot-for-testers --skill unslop-answers
Clone the repo
git clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testers

Made for: Claude Code.

Wrote 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.

agentmods badge for unslop-answers

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/unslop-answers/github.svg)](https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/unslop-answers)
Your own site
<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/unslop-answers"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/unslop-answers/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.

agentmods 80×15 button for unslop-answers

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/unslop-answers"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/unslop-answers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,709 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00151 $0.03709
Opus 5 $0.00076 $0.01854
Sonnet 5 $0.00030 $0.00742
Haiku 4.5 $0.00015 $0.00371

Measured 8d ago against content hash 947a1b7c8fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

unslop-answers 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 8d 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.

plugins/unslop-answers/skills/unslop-answers/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unslop Answers

Cut AI tells from what you say about your own work.

There are two failure modes and they cost very differently. An unreadable answer wastes a reader's minute. An unearned answer costs them a day, because they act on it: they ship on "tests pass", they close the bug on "fixed", they plan around a config option that does not exist. Fluency makes it worse. An answer with no evidence in it reads better than one full of commands and denominators, because nothing in it is qualified.

So this skill has one rule, and every pattern below is a way of noticing where the rule broke.

Every claim is evidenced, quantified, or marked unverified.

When to Use

Always, on any answer about work you did. Explicitly when:

  • reporting a fix, a result, a root cause, or a review finding
  • writing a bug report, a PR description, a commit body, or a release recommendation
  • quoting a number: coverage, pass rate, flake rate, timing, defect count
  • claiming something is absent: no other callers, no other failures, no regressions
  • the request says "prove it", "did you run it", "be specific", "no fluff", "stop hedging"
  • an earlier answer of yours turned out to be wrong and the reason needs finding

Scope and Handoffs

This skill covers what you say: chat replies, reports, findings, plans, docs, commit messages, issue bodies.

  • test code goes to unslop-tests, which judges whether a test proves anything
  • a product feature's output goes to reviewing-ai-output-groundedness, which is a human protocol for auditing a RAG or summarisation feature
  • the complete list of prose style tells lives in ./resources/style-tells.md, for when the job is editing text rather than reporting work

If a finding is about a test being a lie, that is unslop-tests. If it is about you calling that test verified, it is this skill.

Fast Pass

Most answers are routine. Run these six before sending anything, in under a minute.

  1. Did I claim it works? Name the command and paste what it printed, or write "changed, not run".
  2. Is every path, symbol, flag, option, and quote here one I actually saw? Anything typed from memory gets opened and checked, or dropped.
  3. Does every finding carry a file:line?
  4. Does every number carry its denominator and its window?
  5. Did I do less than was asked? Say which part and why, in the first two lines, not the last bullet.
  6. Would this paragraph read identically on a different project? Then it says nothing about this one. Cut it.

Read the full file on GitHub · 219 lines

Files

What ships with it

4 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.

Changes

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.

  1. 8d ago First seen · 219 lines · 151 tokens per session scan A 947a1b7c8fc7

Subscribe to this mod's changes

unslop-answers is a skill published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 16d ago), licensed MIT. It adds 151 tokens to every session and 3,709 once invoked, about $0.0008 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.