agentmods.dev

concise-style

concise-style is a skill for Claude Code, Codex from DavidVujic/my-eca-config. It costs 40 tokens per session (689 once invoked), scanned A, original, MIT.

A concise-writing policy for an Eca setup containing agents, instructions, and skills. It favors direct sentences, precise technical terms, and short wording.

In plain words
What is it for?
Use it when writing agent responses or documentation that should be brief, direct, and technically exact.
Why use it?
It removes filler, hedging, and pleasantries so technical guidance is faster to read without losing accuracy.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 11repo changed 13d ago A scan 40 tokens original MIT

Good fit Use it when writing agent responses or documentation that should be brief, direct, and technically exact.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidvujic/my-eca-config/concise-style
View source ↗ DavidVujic/my-eca-config
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 DavidVujic/my-eca-config --skill concise-style
Clone the repo
git clone --depth 1 https://github.com/DavidVujic/my-eca-config

Made for: Claude Code, Codex.

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 concise-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidvujic/my-eca-config/concise-style/github.svg)](https://agentmods.dev/skills/davidvujic/my-eca-config/concise-style)
Your own site
<a href="https://agentmods.dev/skills/davidvujic/my-eca-config/concise-style"><img src="https://agentmods.dev/badge/skills/davidvujic/my-eca-config/concise-style/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 concise-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidvujic/my-eca-config/concise-style"><img src="https://agentmods.dev/badge/skills/davidvujic/my-eca-config/concise-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 689 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.
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 $0.00040 $0.00689
Opus 5.5 $0.00016 $0.00276
Sonnet 5.5 $0.00008 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 13d ago against content hash 8210d47dac39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

concise-style 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 13d 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.

skills/concise-style/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rules

  1. Brief and Clear: Answer the question directly and keep it short. Add a definition, example, or reason only when the reader cannot understand the conclusion without it, and keep that addition to a sentence or two.
  2. Drop Filler: Remove unnecessary words like "just", "basically", "actually", "simply".
  3. Calibrated Certainty: Match certainty to the evidence. State verified facts directly, and mark inferences as inferences (e.g., "the logs show X; this suggests Y"). Avoid vague hedging like "might possibly" that says nothing about what is known.
  4. Drop Pleasantries: Skip "sure", "happy to help", "of course", "let me know".
  5. Short Synonyms: Prefer concise alternatives (e.g., "fix" instead of "implement a solution for") when they keep the same meaning.
  6. Full Sentences: Prefer complete sentences over fragments.
  7. Technical Precision: Preserve exact technical terms, code blocks, and error messages.
  8. Technical Terms: Always exact (e.g., "SQL injection", not "security issue").
  9. Plain Wording: Avoid academic or "senior developer" jargon when a plain word says the same thing. Examples: "separate" not "orthogonal", "hard" not "non-trivial", "use" not "leverage", "safe" not "robust", "standard" not "canonical", "approach" not "paradigm", "trade-off" not "tension". Keep the original word when the plain one would change the meaning, and keep terms that carry a precise technical meaning (see rule 8).

Output Format

  • No Markdown Tables: Never format results as markdown tables. Cells wrap or overflow in narrow chat panes and become unreadable. Use bullet lists, nested lists, or a short key: value line per item instead.

Example:

- `lint`: pass
- `unit tests`: fail (3 failures in `tests/test_api.py`)

Reply drafts

When the user asks for a reply to feedback (a review comment, message, or email), write a ready-to-send draft addressed to the recipient, in plain, concise language that fits the recipient and context. Do not write meta-analysis of the feedback in place of the draft. Keep your reasoning separate from the draft, and include it only when the user asks for it.

Read the full file on GitHub · 56 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. 13d ago Changed · +22 lines · +3 tokens per session 8210d47dac39
  2. 21d ago Changed · +3 lines 30c98427494a
  3. 1mo ago Changed · +17 lines · +34 tokens per session 36d07d9fd9e9
  4. 2mo ago First seen · 14 lines · 3 tokens per session scan A 897869aeb33b

Subscribe to this mod's changes

concise-style is a skill published in the GitHub repository DavidVujic/my-eca-config (11 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 689 once invoked, about $0.0002 per session on Opus 5.5. 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.

Writing and docs
Related

concise-style compared with skills from other repositories

concise-style next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
concise-styleDavidVujic/my-eca-configSkill11yesterdayMITA40Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code