skill-base-template writing.instructions.md

A set of rules for improving writing while preserving the author's meaning, wording, authority, and level of certainty.

In plain words
What is it for?
It helps revise documentation, procedures, and other technical writing into clear paragraphs, lists, headings, and direct sentences.
Why use it?
It prevents editing from accidentally adding claims, changing responsibility, or making uncertain information sound definite.

Instructions file for GitHub Copilot

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 instructions/techspokes/skill-base-template/writing
Clone the repo
git clone --depth 1 https://github.com/TechSpokes/skill-base-template

Made for: GitHub Copilot.

Per session 181 This file is loaded in full into every session.
When invoked 181 The same file — it is already loaded in full.
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 $0.00181 $0.00181
Opus 5 $0.00090 $0.00090
Sonnet 5 $0.00036 $0.00036
Haiku 4.5 $0.00018 $0.00018

Measured 2d ago against content hash 6cc25f0c5bc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-base-template writing.instructions.md 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 2d 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.

.template/generated/.github/instructions/writing.instructions.md · 19 lines

What it actually says

Writing Instructions

Preserve the author's meaning, vocabulary, authority boundaries, evidence status, and uncertainty before improving style.

  • Put one idea in each paragraph or list item.
  • Keep each paragraph or list item on one physical source line and let renderers wrap it.
  • Name the actor and action when responsibility or permission matters.
  • Prefer direct verbs and concrete nouns over dense label chains.
  • Use headings only when they help readers navigate distinct decisions or procedures.
  • Use lists for genuinely parallel items, not to fragment connected reasoning.
  • Avoid stock transitions, repeated conclusions, and claims of safety that do not name the protected harm.
  • Keep code fences tagged and paths, commands, field names, and user-provided terms exact.

Review generated prose for meaning first, structure second, and sentence quality last. Do not rewrite merely to make the text sound different.

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. 2d ago First seen · 19 lines · 181 tokens per session scan A 6cc25f0c5bc1

Subscribe to this mod's changes

skill-base-template writing.instructions.md is an instructions file published in the GitHub repository TechSpokes/skill-base-template (4 stars, last pushed 1mo ago), licensed MIT. It adds 181 tokens to every session, about $0.0009 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.