unslop

A writing guide that removes patterns often associated with machine-generated text from replies, commit messages, pull requests, documentation and comments.

In plain words
What is it for?
Use it while drafting or tightening text that people will read, including developer communication and project documentation.
Why use it?
It helps prose sound direct and specific instead of padded, vague or formulaic.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/romerma/mstack/unslop
Any agent
npx skills add romerma/mstack --skill unslop
Clone the repo
git clone --depth 1 https://github.com/romerma/mstack

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 891 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00051 $0.00891
Opus 5 $0.00026 $0.00445
Sonnet 5 $0.00010 $0.00178
Haiku 4.5 $0.00005 $0.00089

Measured yesterday against content hash 66eb4adc7c59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unslop 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 yesterday.

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.

skills/unslop/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unslop

Write it clean as you draft it. The cleanup-afterwards pass has been measured to fail, so the rule is not "fix the bad sentence", it is do not generate it.

Content

  1. No puffery. Not "powerful", "seamless", "robust", "comprehensive". Say what it does.
  2. No name-dropping to borrow credibility a claim has not earned.
  3. No superficial -ing clauses. "...enabling teams to move faster" is a sentence that ends without saying anything.
  4. No vague attribution. "It is widely considered" means you do not have a source.
  5. No formulaic challenge framing. "But there is a catch." "Here is the thing."
  6. Every sentence earns its place. If it could appear unchanged in another project's docs, it says nothing about this one. Cut it.

Language

  1. Ban the tell vocabulary: delve, leverage, utilize, robust, seamless, crucial, pivotal, testament, landscape, realm, tapestry, underscore, myriad, plethora, navigate, unlock.
  2. Say "is". Not "serves as", "acts as", "functions as", "represents".
  3. No "not just X, but Y." Say Y.
  4. No rule of three by reflex. Three items because there are three, not for the cadence.
  5. No synonym cycling. The same thing keeps the same name. Renaming it mid-paragraph makes the reader wonder whether it changed.
  6. No false ranges. "From X to Y" only when there is a real spectrum.

Style

  1. No em dashes. If a sentence needs one, it is two sentences.
  2. Colons introduce, they do not join.
  3. Bold marks a term, not emphasis. A paragraph with four bold phrases has none.
  4. No inline-header lists. A bullet is a sentence, not a label plus a dash plus a clause.
  5. Sentence case for headings.
  6. No decorative emoji. A status marker in a table is fine.
  7. Straight quotes.

Communication

  1. No chatbot framing. Not "Great question", not "I hope this helps".
  2. No cutoff disclaimers unless the recency actually affects the answer.
  3. No sycophancy. Agreement is not the default. A recommendation is a judgment, not a validation, and "no" is an acceptable answer.

Read the full file on GitHub · 71 lines

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. yesterday First seen · 71 lines · 51 tokens per session scan A 66eb4adc7c59

Subscribe to this mod's changes

unslop is a skill published in the GitHub repository romerma/mstack (1 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 891 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

happiness-skill

当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.

kangarooking/cangjie-skill · 136 tokens

gsd-audit-milestone

Audit milestone completion against original intent before archiving.

open-gsd/gsd-core · 17 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

spec-kitty-spdd-reasons

Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…

Priivacy-ai/spec-kitty · 118 tokens

conductor-implement

Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.

gemini-cli-extensions/conductor · 34 tokens

review

Review code changes for security, performance, bugs, and quality. Reviews staged changes, unstaged changes, specific commits, or PR-ready diffs.

open-gsd/gsd-pi · 32 tokens