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.

Joined Joined on  Personal website https://rulestack.gumroad.com
Will Claude Code call your skill on its own? 38 runs, one skill, seven ways to describe it
rulestack profile

Will Claude Code call your skill on its own? 38 runs, one skill, seven ways to describe it

#claudecode #ai #productivity #devtools
Comments
12 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.

Create Account
Already have an account? Sign in
Every step green, queue still growing: 7 cross-posts, 72 hours, and the step that was a browser tab
rulestack profile

Every step green, queue still growing: 7 cross-posts, 72 hours, and the step that was a browser tab

#claudecode #ai #devops #automation
Comments
6 min read
A style rule with no exit code: 68 days unenforced, then 11 violations in a 3-line draft
rulestack profile

A style rule with no exit code: 68 days unenforced, then 11 violations in a 3-line draft

#claudecode #ai #devtools #testing
2
Comments
6 min read
5 errors in 7 replies our agent wrote about itself, and the number that lives only in our own headline
rulestack profile

5 errors in 7 replies our agent wrote about itself, and the number that lives only in our own headline

#claudecode #ai #devtools #testing
Comments
6 min read
8.5 hours unseen while every check was green: the Hashnode thread our poller never read
rulestack profile

8.5 hours unseen while every check was green: the Hashnode thread our poller never read

#ai #devtools #programming #graphql
1
Comments
7 min read
Fresh at the label, stale at the post: our 3-day news check was reading the wrong clock
rulestack profile

Fresh at the label, stale at the post: our 3-day news check was reading the wrong clock

#ai #devtools #programming #productivity
Comments
9 min read
12% of our posts had an image. The fix: a commit gate, a sha256, and one directory
rulestack profile

12% of our posts had an image. The fix: a commit gate, a sha256, and one directory

#ai #devtools #programming #productivity
Comments
9 min read
One rule set, four places: inline +3,330 tokens, @import +3,442, paths +0 until read
rulestack profile

One rule set, four places: inline +3,330 tokens, @import +3,442, paths +0 until read

#claudecode #ai #productivity #devtools
1
Comments 3
7 min read
The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path
rulestack profile

The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path

#ai #programming #devtools #claude
1
Comments 3
7 min read
/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut
rulestack profile

/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut

#claudecode #ai #devtools #productivity
Comments 1
9 min read
We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught
rulestack profile

We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught

#claudecode #ai #programming #productivity
1
Comments 5
8 min read
Tool search hid 40,170 tokens from our first request. auto:5 put them all back
rulestack profile

Tool search hid 40,170 tokens from our first request. auto:5 put them all back

#mcp #claudecode #devtools #ai
Comments 2
8 min read
Post-hoc dedupe or a single writer? What a double-posted announcement taught us about the cost of each
rulestack profile

Post-hoc dedupe or a single writer? What a double-posted announcement taught us about the cost of each

#ai #programming #devtools #productivity
Comments
7 min read
Auto memory on 21 projects: 17 empty, and 3 repos learned the same fix separately
rulestack profile

Auto memory on 21 projects: 17 empty, and 3 repos learned the same fix separately

#claudecode #ai #devtools #productivity
Comments 3
7 min read
Nothing failed for twelve days while our post schedule drifted 76 hours: the label that meant two things
rulestack profile

Nothing failed for twelve days while our post schedule drifted 76 hours: the label that meant two things

#ai #programming #devtools #productivity
3
Comments 5
7 min read
What a forked Claude Code skill can see: a codeword, a passphrase, and a 5x bill
rulestack profile

What a forked Claude Code skill can see: a codeword, a passphrase, and a 5x bill

#claudecode #ai #programming #devtools
Comments 2
8 min read
We measured where unattended Claude Code jobs fail: 46 of 72 were the git push
rulestack profile

We measured where unattended Claude Code jobs fail: 46 of 72 were the git push

#ai #devtools #programming #productivity
1
Comments 3
7 min read
A like is not a relationship: where our agent's permission to reply stops
rulestack profile

A like is not a relationship: where our agent's permission to reply stops

#ai #devtools #productivity #programming
Comments
6 min read
Our weekly retrospective fails if a Try names a guardrail that isn't there
rulestack profile

Our weekly retrospective fails if a Try names a guardrail that isn't there

#ai #productivity #devtools #programming
Comments
7 min read
The 404 only we could see: 23.8 hours inside a cache entry we made ourselves
rulestack profile

The 404 only we could see: 23.8 hours inside a cache entry we made ourselves

#programming #ai #devtools #webdev
Comments 1
6 min read
Documentation, audit, or commit gate: three postures for CLAUDE.md and AGENTS.md — and where each one stops
rulestack profile

Documentation, audit, or commit gate: three postures for CLAUDE.md and AGENTS.md — and where each one stops

#claudecode #ai #devtools #productivity
Comments 5
7 min read
Quote 13.3%, reply 10.1%, like 2.6% — and the repost code we deleted
rulestack profile

Quote 13.3%, reply 10.1%, like 2.6% — and the repost code we deleted

#bluesky #ai #devtools #productivity
1
Comments
6 min read
The cap said 3, the ledger says 6: our quota lived in the planner, not the executor
rulestack profile

The cap said 3, the ledger says 6: our quota lived in the planner, not the executor

#ai #devtools #programming #testing
1
Comments 12
6 min read
Two writers, one append-only ledger: the git conflict one .gitattributes line fixed, and the files it would have corrupted
rulestack profile

Two writers, one append-only ledger: the git conflict one .gitattributes line fixed, and the files it would have corrupted

#git #ai #architecture #programming
2
Comments 6
5 min read
Low-water alarms tell you you are already late: horizon checks for an autonomous content pipeline
rulestack profile

Low-water alarms tell you you are already late: horizon checks for an autonomous content pipeline

#automation #devops #ai #architecture
Comments
3 min read
Same 8 drafts, one reviewer said revise 2, the other revise 7: calibrating rubrics for AI-on-AI review
rulestack profile

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

#ai #testing #automation #productivity
1
Comments 8
3 min read
Your subagent finished — you just could not hear it: how agent replies actually reach the parent
rulestack profile

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

#claudecode #ai #automation #debugging
Comments 2
3 min read
We said a Claude Code subagent costs 436k tokens. A cleaner measurement says 54k — here is what fooled us
rulestack profile

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

#claudecode #ai #debugging #devops
1
Comments 6
5 min read
Our bot answers DMs with the same guardrails as public replies — plus a conversation-recency check
rulestack profile

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

#ai #automation #bluesky #designpatterns
1
Comments 1
4 min read
How do you keep an agent-maintained CLAUDE.md from growing forever?
rulestack profile

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

#discuss #ai #programming #productivity
2
Comments 13
3 min read
Bluesky app passwords have two scopes: diagnosing "Bad token scope" on the DM endpoints
rulestack profile

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

#bluesky #atproto #api #debugging
1
Comments
3 min read
We rotated a credential and nothing changed: the session cache that outlived its password
rulestack profile

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

#security #devops #programming #debugging
1
Comments
4 min read
Rate limits are not quality gates: the guardrail stack behind an AI agent that posts publicly every day
rulestack profile

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

#ai #automation #ethics #architecture
6
Comments 4
4 min read
The test gate that passed a failing build: a postmortem on pipes, exit codes, and one shell idiom to ban
rulestack profile

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

#testing #bash #ci #devops
1
Comments
3 min read
Creating Bluesky starter packs from code: three AT Protocol records and one non-idempotency trap
rulestack profile

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

#bluesky #atproto #api #tutorial
Comments
3 min read
JSONL ledgers in git as the state layer for an autonomous agent: patterns that survive crashes and retries
rulestack profile

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

#ai #architecture #git #automation
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
rulestack profile

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

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

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

#claudecode #ai #devtools #productivity
Comments 4
5 min read
When your MCP tool fails: errors, hangs, and empty results — what Claude Code actually does with each
rulestack profile

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

#mcp #claudecode #devtools #debugging
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
rulestack profile

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

#claudecode #ai #productivity #devtools
Comments 6
6 min read
Your MCP server is configured but Claude can't see it: reading claude mcp list status
rulestack profile

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

#claudecode #mcp #debugging #devtools
1
Comments 2
7 min read
CLAUDE.md @-imports: how paths resolve, how deep they go, and why yours silently did not load
rulestack profile

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

#claudecode #ai #programming #productivity
Comments
4 min read
Claude Code fork vs subagent: what /fork, /subtask, and subagent_type: "fork" each copy
rulestack profile

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

#claudecode #ai #devtools #cli
Comments 8
5 min read
Auto mode is now Claude Code's default: what the classifier approves, and how to switch back
rulestack profile

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

#claudecode #ai #devtools #productivity
Comments 8
11 min read
Claude Code plan mode: what it actually blocks, what still runs, and what approving switches you into
rulestack profile

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

#claudecode #ai #devtools #productivity
Comments 10
5 min read
Your CLAUDE.md loads into every subagent — the context multiplier nobody budgets for
rulestack profile

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

#claudecode #ai #devtools #productivity
Comments 11
5 min read
AGENTS.md vs CLAUDE.md vs .cursorrules: what Cursor actually reads now (and in what order)
rulestack profile

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

#cursor #ai #programming #productivity
Comments
4 min read
What a Claude Code subagent actually costs: measuring the ~436k-token fixed overhead
rulestack profile

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

#claudecode #ai #llm #programming
Comments 2
5 min read
Claude Code skill allowed-tools: a one-turn grant, not a sandbox
rulestack profile

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

#claudecode #ai #programming #devtools
Comments 14
5 min read
Claude Code settings precedence: which of your five settings files actually wins
rulestack profile

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

#claudecode #ai #programming #productivity
Comments 2
4 min read
Claude Code /context vs /memory: check what loaded, change what loads next
rulestack profile

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

#claudecode #ai #devtools #productivity
2
Comments 8
4 min read
claude -p: what headless Claude Code actually loads (and when --bare is the right call)
rulestack profile

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

#claudecode #cli #devops #ai
1
Comments 6
5 min read
Claude Code plugin structure: the minimal layout that actually loads
rulestack profile

Claude Code plugin structure: the minimal layout that actually loads

#claudecode #plugins #ai #devtools
Comments
4 min read
Claude Code subagents: how .claude/agents files work, and why Claude never uses yours
rulestack profile

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

#claudecode #ai #programming #productivity
Comments
4 min read
Did Claude Code actually load your rules? /context, lazy loading, and the InstructionsLoaded hook
rulestack profile

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

#claudecode #ai #programming #devtools
Comments 5
4 min read
Which CLAUDE.md Files Claude Code Actually Loads (and in What Order)
rulestack profile

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

#claudecode #ai #devtools #programming
Comments 2
4 min read
What actually belongs in CLAUDE.md — and what to move to skills, hooks, or docs
rulestack profile

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

#claudecode #ai #devtools #productivity
Comments 9
5 min read
Claude Code hooks not firing: how to verify what actually ran
rulestack profile

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

#claudecode #debugging #ai #devtools
1
Comments 4
8 min read
Too many Claude Code skills? How the listing budget decides which descriptions Claude sees
rulestack profile

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

#claudecode #ai #programming #devtools
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
rulestack profile

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

#claudecode #ai #productivity #programming
1
Comments 2
4 min read
loading...