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 agentmods add instructions/randynorthrup/high-quality-projects-skill/agents-mdgit clone --depth 1 https://github.com/RandyNorthrup/high-quality-projects-skillWrote 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/instructions/randynorthrup/high-quality-projects-skill/agents-md)<a href="https://agentmods.dev/instructions/randynorthrup/high-quality-projects-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/randynorthrup/high-quality-projects-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01209 | $0.01209 |
| Opus 5 | $0.00605 | $0.00605 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
high-quality-projects-skill 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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Entry point for coding agents that support AGENTS.md, or for any agent
explicitly directed to this file.
This package holds two vendor-neutral workflows and the configuration they install. The Claude Code, Cursor, and Copilot files are optional packaging and discovery adapters around that shared content.
The two workflows
| Workflow | Read this file | Use when |
|---|---|---|
| Project setup | skills/project_setup/SKILL.md |
Starting a new project. Grills the idea, confirms a project brief, then scaffolds. |
| Quality retrofit | skills/quality_retrofit/SKILL.md |
An existing codebase needs standards applied. |
They are plain Markdown instructions. Read the whole file before acting on it — both open with a mandatory scan step that must run before anything is created or modified.
The directory is named skills/ because Claude Code requires that layout to
load them as plugin skills. The files themselves are vendor-neutral; the name is
packaging, not a dependency.
Resolving paths
The instructions use ${SKILL_ROOT}/... as a placeholder for this package's
root. Resolve it with the script for the active shell. On Windows PowerShell:
$SkillRoot = & 'C:\path\to\high-quality-projects-skill\scripts\skill-root.ps1'
On Linux, macOS, or another POSIX environment:
SKILL_ROOT="$(bash /path/to/high-quality-projects-skill/scripts/skill-root.sh)"
Both scripts locate themselves, so they work from a git clone, a vendored copy,
or a submodule with no environment configured. They honour SKILL_ROOT first,
then CLAUDE_PLUGIN_ROOT (which Claude Code sets automatically), then fall back
to their own location. Do not invoke Windows bash.exe: it can be a WSL relay
even when no Linux distribution or /bin/bash exists.
If your agent cannot execute shell commands, ignore the variable and read the
files directly — templates/ is plain configuration and the workflows are plain
instructions.
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.
- 4d ago First seen · 111 lines · 1,209 tokens per session scan A a5f103b0035e
high-quality-projects-skill AGENTS.md is an instructions file published in the GitHub repository RandyNorthrup/high-quality-projects-skill (1 stars, last pushed 12d ago), licensed MIT. It adds 1,209 tokens to every session, about $0.0060 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.
Other instructions, from other repositories
procoder tests.instructions.md
Instructions for azrtydxb/procoder, covering tests in procoder, every test carries its mutation, assertions, portability and fixtures.
procoder copilot-instructions.md
Copilot instructions for azrtydxb/procoder, covering procoder, the contract, the work chain, parallel work and which command, right now.
procoder go.instructions.md
Instructions for azrtydxb/procoder, covering go in procoder, no silent green, p-control: the binary prints, the agent writes, paths and arguments and exit codes are the public interface.
procoder workflows.instructions.md
Instructions for azrtydxb/procoder, covering ci in procoder, pins, actions and honesty in a job.
procoder docs.instructions.md
Instructions for azrtydxb/procoder, covering prose in procoder, what the docs must keep in step with, the changelog, specs and tone.
procoder AGENTS.md
AGENTS.md instructions for azrtydxb/procoder, covering procoder, the contract, the work chain, parallel work and which command, right now.