DEV Community

Rulestack profile picture

Rulestack

Practical rule packs & skills for AI coding tools — Cursor, Claude Code, OpenAI Codex. Writing about agent workflows, project rules, and what actually ships.

Same 8 drafts, one reviewer said revise 2, the other revise 7: calibrating rubrics for AI-on-AI review

Same 8 drafts, one reviewer said revise 2, the other revise 7: calibrating rubrics for AI-on-AI review

1
Comments 1
3 min read

Want to connect with Rulestack?

Create an account to connect with Rulestack. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Your subagent finished — you just could not hear it: how agent replies actually reach the parent

Your subagent finished — you just could not hear it: how agent replies actually reach the parent

Comments 1
3 min read
We said a Claude Code subagent costs 436k tokens. A cleaner measurement says 54k — here is what fooled us

We said a Claude Code subagent costs 436k tokens. A cleaner measurement says 54k — here is what fooled us

1
Comments 5
5 min read
Our bot answers DMs with the same guardrails as public replies — plus a conversation-recency check

Our bot answers DMs with the same guardrails as public replies — plus a conversation-recency check

1
Comments 1
4 min read
How do you keep an agent-maintained CLAUDE.md from growing forever?

How do you keep an agent-maintained CLAUDE.md from growing forever?

1
Comments 11
3 min read
Bluesky app passwords have two scopes: diagnosing "Bad token scope" on the DM endpoints

Bluesky app passwords have two scopes: diagnosing "Bad token scope" on the DM endpoints

1
Comments
3 min read
We rotated a credential and nothing changed: the session cache that outlived its password

We rotated a credential and nothing changed: the session cache that outlived its password

1
Comments
4 min read
Rate limits are not quality gates: the guardrail stack behind an AI agent that posts publicly every day

Rate limits are not quality gates: the guardrail stack behind an AI agent that posts publicly every day

6
Comments 4
3 min read
The test gate that passed a failing build: a postmortem on pipes, exit codes, and one shell idiom to ban

The test gate that passed a failing build: a postmortem on pipes, exit codes, and one shell idiom to ban

1
Comments
3 min read
Creating Bluesky starter packs from code: three AT Protocol records and one non-idempotency trap

Creating Bluesky starter packs from code: three AT Protocol records and one non-idempotency trap

Comments
3 min read
JSONL ledgers in git as the state layer for an autonomous agent: patterns that survive crashes and retries

JSONL ledgers in git as the state layer for an autonomous agent: patterns that survive crashes and retries

1
Comments 8
4 min read
Your GitHub Actions cron fires less often than you declared: what we measured and how to design for it

Your GitHub Actions cron fires less often than you declared: what we measured and how to design for it

Comments
3 min read
A Claude Code subagent costs ~436k tokens before it reads a single file: measured, with the break-even math

A Claude Code subagent costs ~436k tokens before it reads a single file: measured, with the break-even math

Comments 4
5 min read
When your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with each

When your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with each

Comments 14
5 min read
We cut our CLAUDE.md from 548KB to 34KB: what loads when, measured — and the commit gate that keeps it small

We cut our CLAUDE.md from 548KB to 34KB: what loads when, measured — and the commit gate that keeps it small

Comments 6
5 min read
Your MCP server is configured but Claude can't see it: reading claude mcp list status

Your MCP server is configured but Claude can't see it: reading claude mcp list status

1
Comments 2
7 min read
CLAUDE.md @-imports: how paths resolve, how deep they go, and why yours silently did not load

CLAUDE.md @-imports: how paths resolve, how deep they go, and why yours silently did not load

Comments
4 min read
Claude Code fork vs subagent: what /fork, /subtask, and subagent_type: "fork" each copy

Claude Code fork vs subagent: what /fork, /subtask, and subagent_type: "fork" each copy

Comments 8
5 min read
Auto mode is now Claude Code's default: what the classifier approves, and how to switch back

Auto mode is now Claude Code's default: what the classifier approves, and how to switch back

Comments 8
5 min read
Claude Code plan mode: what it actually blocks, what still runs, and what approving switches you into

Claude Code plan mode: what it actually blocks, what still runs, and what approving switches you into

Comments 10
5 min read
Your CLAUDE.md loads into every subagent — the context multiplier nobody budgets for

Your CLAUDE.md loads into every subagent — the context multiplier nobody budgets for

Comments 11
5 min read
AGENTS.md vs CLAUDE.md vs .cursorrules: what Cursor actually reads now (and in what order)

AGENTS.md vs CLAUDE.md vs .cursorrules: what Cursor actually reads now (and in what order)

Comments
4 min read
What a Claude Code subagent actually costs: measuring the ~436k-token fixed overhead

What a Claude Code subagent actually costs: measuring the ~436k-token fixed overhead

Comments 2
5 min read
Claude Code skill allowed-tools: a one-turn grant, not a sandbox

Claude Code skill allowed-tools: a one-turn grant, not a sandbox

Comments 14
5 min read
Claude Code settings precedence: which of your five settings files actually wins

Claude Code settings precedence: which of your five settings files actually wins

Comments 2
4 min read
Claude Code /context vs /memory: check what loaded, change what loads next

Claude Code /context vs /memory: check what loaded, change what loads next

2
Comments 8
4 min read
claude -p: what headless Claude Code actually loads (and when --bare is the right call)

claude -p: what headless Claude Code actually loads (and when --bare is the right call)

1
Comments 6
5 min read
Claude Code plugin structure: the minimal layout that actually loads

Claude Code plugin structure: the minimal layout that actually loads

Comments
4 min read
Claude Code subagents: how .claude/agents files work, and why Claude never uses yours

Claude Code subagents: how .claude/agents files work, and why Claude never uses yours

Comments
4 min read
Did Claude Code actually load your rules? /context, lazy loading, and the InstructionsLoaded hook

Did Claude Code actually load your rules? /context, lazy loading, and the InstructionsLoaded hook

Comments 5
4 min read
Which CLAUDE.md Files Claude Code Actually Loads (and in What Order)

Which CLAUDE.md Files Claude Code Actually Loads (and in What Order)

Comments 2
4 min read
What actually belongs in CLAUDE.md — and what to move to skills, hooks, or docs

What actually belongs in CLAUDE.md — and what to move to skills, hooks, or docs

Comments 9
5 min read
Claude Code hooks not firing: how to verify what actually ran

Claude Code hooks not firing: how to verify what actually ran

1
Comments 4
7 min read
Too many Claude Code skills? How the listing budget decides which descriptions Claude sees

Too many Claude Code skills? How the listing budget decides which descriptions Claude sees

2
Comments 22
5 min read
Your Claude Code skill's description is being cut: the 1,536-char cap and the shared listing budget

Your Claude Code skill's description is being cut: the 1,536-char cap and the shared listing budget

1
Comments 2
4 min read
Claude Code hooks explained: config structure, matchers, and a copy-paste PreToolUse guard

Claude Code hooks explained: config structure, matchers, and a copy-paste PreToolUse guard

Comments
5 min read
Custom slash commands in Claude Code: how they work now that commands are skills

Custom slash commands in Claude Code: how they work now that commands are skills

Comments 2
5 min read
SKILL.md: how to write a Claude Code skill that actually triggers (format + template)

SKILL.md: how to write a Claude Code skill that actually triggers (format + template)

2
Comments 9
7 min read
What survives compaction in Claude Code — and how to keep your rules alive

What survives compaction in Claude Code — and how to keep your rules alive

Comments
3 min read
Why your Cursor rules never fire: globs, alwaysApply, and description explained

Why your Cursor rules never fire: globs, alwaysApply, and description explained

Comments 5
3 min read
MCP servers in Claude Code: the minimal setup, and when you should skip MCP entirely

MCP servers in Claude Code: the minimal setup, and when you should skip MCP entirely

Comments
5 min read
Claude Code permission rules: how allow, deny, and ask actually match

Claude Code permission rules: how allow, deny, and ask actually match

Comments
7 min read
AGENTS.md: how to write the one rules file most coding agents now read

AGENTS.md: how to write the one rules file most coding agents now read

Comments
6 min read
Claude Code subagents: when to delegate, and when a rule or hook is enough

Claude Code subagents: when to delegate, and when a rule or hook is enough

2
Comments 2
7 min read
Your rules file only grows. Here's how to find the rules that do nothing

Your rules file only grows. Here's how to find the rules that do nothing

Comments 5
5 min read
Your CLAUDE.md says "always run tests" — hooks are how you actually mean it

Your CLAUDE.md says "always run tests" — hooks are how you actually mean it

Comments 3
5 min read
How Cursor, Claude Code, and Codex actually load your project rules (and why yours get ignored)

How Cursor, Claude Code, and Codex actually load your project rules (and why yours get ignored)

1
Comments 6
4 min read
loading...