What is dw-solo-skills AGENTS.md?

Repository instructions for dw-solo-skills, a catalogue of coding-agent skills and supporting scripts. They define where skills, plugins, setup files, documentation, and validation tests belong.

Adding or editing skills, maintaining plugin links and setup scripts, routing longer guidance into topic files, and validating documentation and shell tests.

They keep the catalogue organized and within its documented size and structure rules. They also ensure that updates are made in the canonical skill file and checked before pushing.

How dominikwozniak/dw-solo-skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to dominikwozniak/dw-solo-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/dominikwozniak/dw-solo-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/dominikwozniak/dw-solo-skills

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dominikwozniak/dw-solo-skills/agents-md/github.svg)](https://agentmods.dev/instructions/dominikwozniak/dw-solo-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/dominikwozniak/dw-solo-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dominikwozniak/dw-solo-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dominikwozniak/dw-solo-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dominikwozniak/dw-solo-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,995 This file is loaded in full into every session.

When invoked 1,995 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.

Model	Per session	Once invoked
Fable 5.1	$0.01995	$0.01995
Opus 5	$0.00997	$0.00997
Sonnet 5	$0.00399	$0.00399
Haiku 4.5	$0.00199	$0.00199

Measured 3d ago against content hash 22bb5f4181df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dw-solo-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 3d 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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dw-solo-skills — agent instructions

CLAUDE.md is a symlink to this file — edit AGENTS.md. Budget: 120 lines / 10 KB, enforced by pnpm validate:docs. Over budget is not a licence to trim a rule: move a topic into docs/agents/<topic>.md and add its Task Router row, in the same commit. A trap learned the hard way is appended to that topic file's ## Gotchas, never to this one. See docs/agents/README.md.

A skills catalog, not a code project. Keep it thin: every skill here assumes one reader.

Layout — and the one rule

skills/<name>/SKILL.md           the canon for every skill — agents/<name>.md for every agent. EDIT HERE.
plugins/dw-solo/                 the loop plugin — plugin.json + symlinks (mode 120000) → the canon
plugins/dw-solo-setup/           the setup plugin — dw-init, dw-doctor, the templates symlink
plugins/dw-solo-extras/          off-loop — dw-grain, dw-handoff, dw-prune, dw-unslop + agents dw-decisions, dw-docs-drift
scripts/runtime/<script>.sh      shipped scripts — symlinked into the owning plugin
scripts/<script>.{sh,mjs}        repo CI tooling, never shipped (validate-*.sh, check-skill-corpus.mjs)
scripts/tests/<script>.test.sh   bash self-tests
evals/cases/<name>.json          routing cases — one per model-invocable skill, never shipped
evals/behaviour/<name>.json      behaviour cases + evals/fixtures/ — model-in-the-loop, opt-in
evals/routing.ts                 the routing eval — free, deterministic, in CI
templates/                       payload copied INTO a target project — hooks, settings.json,
                                 AGENTS.md, check-agents-docs.mjs, gitignore-block.txt,
                                 worktreeinclude.txt, the .ai/ and docs/decisions/ READMEs
.claude-plugin/marketplace.json  makes this repo installable as a plugin source

Always edit the canon above; use it instead of any plugins/… path, since every one of those is a symlink back to it — plugins/*/skills/, scripts/ and templates/ alike. That rule is absolute. Why it works, and what a plugin must own for it to keep working: docs/agents/skills-and-plugins.md.

Read the full file on GitHub · 121 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.

3d ago Changed · +3 tokens per session 22bb5f4181df
5d ago Changed · +1 lines · +36 tokens per session 5ef08f80930d
7d ago Changed · +2 lines · +108 tokens per session a2817d88fb50
11d ago First seen · 118 lines · 1,848 tokens per session scan A 953dc13195cc

Subscribe to this mod's changes

dw-solo-skills AGENTS.md is an instructions file published in the GitHub repository dominikwozniak/dw-solo-skills (2 stars, last pushed today), licensed MIT. It adds 1,995 tokens to every session, about $0.0100 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.

Claude Code agent-skills claude claude-code-plugin workflow

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

dw-solo-skills: Instructions file for Claude Code