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 fatihguner/foreman --skill clarity-and-concisiongit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/clarity-and-concision)<a href="https://agentmods.dev/skills/fatihguner/foreman/clarity-and-concision"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/clarity-and-concision/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/fatihguner/foreman/clarity-and-concision"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/clarity-and-concision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00098 | $0.04009 |
| Opus 5 | $0.00049 | $0.02005 |
| Sonnet 5 | $0.00020 | $0.00802 |
| Haiku 4.5 | $0.00010 | $0.00401 |
Grade A, and why
clarity-and-concision 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 5d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Clarity and Concision
Consider a mid-sized company where 200 professionals each write an average of 10 internal messages per day, each message averaging 150 words. That is 300,000 words produced daily -- roughly three novels. Now suppose that 30% of those words are unnecessary. The organisation is generating 90,000 wasted words every working day. At an average reading speed of 250 words per minute, that is 360 person-hours per day spent reading words that should never have been written. Six full-time employees, year-round, doing nothing but reading padding. The financial cost of corporate verbosity is not metaphorical. It is measurable, and it is staggering.
Clarity and concision are not aesthetic preferences. They are economic imperatives.
The Framework
Clarity as Courage
Clarity is a double-edged sword. When a writer takes a position or recommends a course of action, the writing is clear -- and the writer is exposed. People who do not want to commit make their writing muddy on purpose. They leave room to claim credit for good outcomes and deny responsibility for bad ones. Readers, however, perceive this not as strategic ambiguity but as spinelessness. Clear writing requires taking a stand.
The test for clarity is simple: show the draft to a colleague who has no context and ask them to identify the three main points. If they cannot do so accurately after one read-through, the writing is not clear enough.
The Research Case for Less
The intuition that shorter is better has been validated experimentally, at scale. Writing for Busy Readers reports a field experiment in which two versions of an email were sent to 7,002 school board members across the United States requesting completion of a short online survey. One email contained 127 words; the other contained 49 words. The 49-word version produced nearly double the response rate -- 4.8% versus 2.7%. The survey itself was identical in both conditions. Some recipients likely looked at the longer email and declined to engage at all. Others read partway through and never reached the request. Still others used the email's length as a proxy for how long the survey would take: 29% of those who saw the concise version estimated the survey at under five minutes, compared with just 15% of those who saw the longer version.
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.
- 5d ago Changed · +244 lines · +98 tokens per session f52eb7f29092
- 11d ago First seen · 1 lines · 0 tokens per session scan A 3c1f670d6590
clarity-and-concision is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 4,009 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
jargon-flagger
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.
redundancy-checker
Scans a draft for repeated ideas, redundant phrases, and unnecessary word clusters, then delivers a flagged report and a tightened version of the text without altering meaning or voice.
passive-voice-checker
Identifies every passive-voice construction in a draft, assesses whether each weakens or serves the prose, and offers active-voice alternatives for those that should be changed — while leaving justified passives alone.
ai-writing-detox
Rewrites AI-flavoured copy into a publishable register by stripping the language tells of an LLM draft — buzzwords, throat-clearing, false-inclusive openers, and the "not just X — Y" rhetorical tic — and supplies the canonical banned-list that runtime hooks read to flag drafts before they ship.
copy-editor
Copy-edit a piece of text for clarity, consistency, style, and readability — going beyond proofreading to tighten prose, improve sentence structure, and enforce consistent style throughout, while flagging substantive issues for the author's attention.
ai-slop-detector
Use when the user asks to audit, score, humanize, or fix prose for AI-writing signals or readability. Produces separate AI-slop and comprehension findings with actionable edits.