agentmods.dev

writing-skills: Instructions file for Codex

AGENTS.md

writing-skills AGENTS.md is an instructions file for Codex, OpenCode from surendranb/writing-skills. It costs 513 tokens per session, scanned A, original, MIT.

Repository instructions for a collection of writing skills stored as Markdown files. The skills define writing frameworks and voices, and automated checks enforce their required structure.

In plain words
What is it for?
Use them when creating, editing, validating, or packaging writing skills and their plugin files.
Why use it?
They make each writing skill consistent, testable, and easy for both people and coding agents to use or maintain.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions Claude Code; mentions AGENTS.md.

This is surendranb/writing-skills's own configuration. It tells Codex and OpenCode how to work on writing-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything writing-skills configures →

not rated 53repo +1 changed 2mo ago A scan 513 tokens original MIT
View source ↗ surendranb/writing-skills
Reuse

Borrowing it

Nothing to install: this file belongs to surendranb/writing-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/surendranb/writing-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/surendranb/writing-skills

Made for: Codex, OpenCode.

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 writing-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/surendranb/writing-skills/agents-md/github.svg)](https://agentmods.dev/instructions/surendranb/writing-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/surendranb/writing-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/surendranb/writing-skills/agents-md/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 writing-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/surendranb/writing-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/surendranb/writing-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 513 This file is loaded in full into every session.
When invoked 513 The same file — it is already loaded in full.
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 $0.00513 $0.00513
Opus 5.5 $0.00205 $0.00205
Sonnet 5.5 $0.00103 $0.00103
Haiku 4.5 $0.00051 $0.00051

Measured 2mo ago against content hash 61051ebacdfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

writing-skills AGENTS.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 2mo 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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — writing-skills

Repo map and contracts for agents working in this repository.

What this is

16 writing-style skills as SKILL.md files: 9 frameworks (measurable standards with hard checks) and 7 voices (character registers with mechanical rules). Pure text — this repo contains skills and their packaging, nothing else.

Layout

skills/<name>/SKILL.md      one skill per folder; frontmatter name == folder name
.claude-plugin/             Claude Code marketplace + plugin manifests
plugin.json                 Agent Plugins 1.0 manifest (Codex, Kiro, ...)
package.json / pyproject.toml   npm / PyPI packaging (plugin.json + skills/ only)
template/SKILL.md           skeleton for new skills
scripts/validate_skills.py  the CI gate — run it before any commit

The skill anatomy contract (enforced by CI)

  1. Frontmatter: name matching the folder; description >= 80 chars containing "Use when" with concrete trigger phrases.
  2. ## The core rule — one bolded sentence that IS the skill, plus a workflow line.
  3. ## Mechanics — numbered, each one verifiable (a cap, a ban list, a ratio).
  4. ## Verify — the checklist an agent must pass before delivering.
  5. ## Do not — the anti-patterns.
  6. At least two before/after transform examples.
  7. Total length <= 120 lines.

Framework skills must cite the real standard and match it — verify rules against the source, not memory. Fidelity errors are bugs.

Working here

  • Validate after any change: python3 scripts/validate_skills.py
  • New skill: copy template/SKILL.md into skills/<name>/, fill it, add the path to .claude-plugin/marketplace.json, validate.
  • Keep this repo skills-only: no servers, no scripts beyond the validator, no config that runs anything on install.

Releases

Every skill addition or plugin improvement = a release: bump the version in plugin.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json (metadata.version), package.json, pyproject.toml (CI fails on mismatch); add a CHANGELOG entry; tag vX.Y.Z + GitHub release; npm publish manually.

Read the full file on GitHub · 51 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. 2mo ago Changed 61051ebacdfb
  2. 2mo ago First seen · 51 lines · 513 tokens per session scan A e59aebaf0f2e

Subscribe to this mod's changes

writing-skills AGENTS.md is an instructions file published in the GitHub repository surendranb/writing-skills (53 stars, last pushed 2mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0021 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 docsagent-skillsai-agentsclaude-code-plugincodexgemini-cli-extension
Related

writing-skills AGENTS.md compared with instructions from other repositories

writing-skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
writing-skills AGENTS.mdsurendranb/writing-skillsInstructions file532mo agoMITA513Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode