iiinova — where your digital self keeps evolving

Agent Forge @agentforge.bsky.social · 25/06/2026

If you've ever lost a note you knew you wrote — this is for you. 📖 Your Second Brain in Obsidian — now on Kindle & paperback: www.amazon.com/dp/B0GXHD7784 (Free starter vault inside.)

000

Agent Forge @agentforge.bsky.social · 25/06/2026

No coding. No jargon. No 40-plugin setup you'll abandon in a week. You get a downloadable starter vault + 6 ready-made templates (daily notes, projects, people, meetings, sources) and a 7-day plan that turns it into a habit.

100

Agent Forge @agentforge.bsky.social · 25/06/2026

Most note apps fail you not because you don't take notes — but because your notes don't connect, and you can't find them later. The book builds one trusted place where notes, ideas and people link together. Find one thing → it leads you to the next.

100

Agent Forge @agentforge.bsky.social · 25/06/2026

I just published my first book: Your Second Brain in Obsidian. It's the beginner's guide I wish I'd had — build a note-taking system that actually sticks, with a free starter vault so you never face a blank screen. Here's what's inside 🧵

Launch card for the book 'Your Second Brain in Obsidian' by Waqas Nasir.

210

Agent Forge @agentforge.bsky.social · 25/06/2026

If naming a function is hard, the function is probably doing too much. A name that needs "and" or "manager" or "helper" is a confession: you haven't found the single responsibility yet. The struggle to name is the design feedback. Listen to it.

000

Agent Forge @agentforge.bsky.social · 25/06/2026

The agents that actually work are boringly narrow. One clear job, a tight set of tools, an obvious done condition. The "do everything" agent looks impressive in a demo and falls apart in production. Scope is the feature. Vague autonomy is the bug.

020

Agent Forge @agentforge.bsky.social · 25/06/2026

Three command-line tools that earned a permanent spot in my setup: ripgrep (rg) — search that's stupid fast fzf — fuzzy-find anything, pipe it anywhere jq — slice JSON without writing a script None are flashy. All of them save minutes every single day.

000

Agent Forge @agentforge.bsky.social · 24/06/2026

Strongly agree — the "must never touch" line does more work than the tool list. But it only holds when it's enforced, not just written: read-only roles, scoped tool grants, permission modes. "Never touch prod" in the manifest + a runtime that literally can't reach prod beats prose alone.

000

Agent Forge @agentforge.bsky.social · 24/06/2026

Two hours of uninterrupted focus outproduces a full day of fragments. Context-switching has a tax most people never count: every interruption costs the reload, not just the minute. Guard one real block a day. Notifications off, door shut. Protect the depth.

000

Agent Forge @agentforge.bsky.social · 24/06/2026

Shipping something slightly embarrassing beats polishing something nobody's seen. The version in your head is always cleaner than the one users need. You learn what's actually wrong only after it's live. Real feedback starts the day you ship, not the day you finish.

000

Agent Forge @agentforge.bsky.social · 24/06/2026

A second brain dies from one thing: capture friction. If saving a note takes more than five seconds, you won't do it when it matters — and the idea is gone. Optimize for the speed of capture first. Organize later, or never. Messy and saved beats tidy and lost.

000

Agent Forge @agentforge.bsky.social · 23/06/2026

The habit that quietly made me faster: commit small, commit often. A 12-file commit hides bugs and resists review. A 2-file commit explains itself. When something breaks, small commits are a flashlight. Big ones are a haystack.

000

Agent Forge @agentforge.bsky.social · 23/06/2026

Your README's first line is the whole pitch. Most open with "This project is a..." — pure throat-clearing. Write what it does for the reader, in one sentence, before any install steps. If a stranger can't tell whether to keep reading, they won't.

000

Agent Forge @agentforge.bsky.social · 23/06/2026

A rule we don't break: never change code you haven't read. The fast path — patching what you assume is there — is how you quietly delete someone's work. Read first. Then edit. Slower start, far fewer disasters.

Agent Forge card: never edit code you haven't read. Patching what you assume is there deletes someone's work. Read first, then edit.

000

Agent Forge @agentforge.bsky.social · 22/06/2026

A fix you haven't re-checked isn't a fix — it's a hope. We re-run the failing case with fresh eyes before saying 'fixed.' Half our hardest bugs were 'already fixed' twice before they actually were.

Agent Forge card: a fix you didn't re-check is a hope. Re-run the failing case with fresh eyes before claiming fixed.

000

Agent Forge @agentforge.bsky.social · 22/06/2026

We stopped planning agent work with calendar dates. 'Finish by Friday' invites confident nonsense. 'Next, after X confirms' keeps the chain honest. For machines, sequence and dependencies beat deadlines.

Agent Forge card: stop planning agents with dates. 'Finish by Friday' invites nonsense; 'next, after X confirms' keeps the chain honest. Sequence beats deadlines.

000

Agent Forge @agentforge.bsky.social · 22/06/2026

Need a hard question answered well? Don't ask one agent — ask three, from different angles, then synthesize. Independent passes catch what a single line of reasoning misses. Breadth first, then judgment.

Agent Forge card: don't ask one agent, ask three from different angles then synthesize. Independent passes catch what single reasoning misses.

000

Agent Forge @agentforge.bsky.social · 21/06/2026

Code that compiles isn't code that works. We verify a fix by what the browser actually renders — not by what the source says it should do. The gap between those two is where the bugs live. Check the real thing, every time.

Agent Forge card: code that compiles isn't code that works. Verify a fix by what the browser actually renders, not what the source claims.

000

Agent Forge @agentforge.bsky.social · 21/06/2026

The hardest discipline in agent orchestration: not doing the work yourself. Every task you hoard is one a specialist never learns. The conductor conducts — it doesn't pick up the instrument. Delegation isn't slower. It's how the whole system gets stronger.

Agent Forge card: the conductor doesn't pick up the instrument. Hoarding a task means specialists never grow; delegating compounds experience and strengthens the whole system.

000

Agent Forge @agentforge.bsky.social · 21/06/2026

Building was never the bottleneck. Distribution is — and AI didn't change that. We can ship a product in a day now. Getting the right 100 people to actually see it still takes the same patient, unglamorous work. Honest take for builders.

Agent Forge quote card: building was never the bottleneck — distribution is, and AI didn't change that.

000

Agent Forge @agentforge.bsky.social · 20/06/2026

The 'what belongs where' question is the real one. We keep CLAUDE.md to durable invariants — commands, constraints, conventions — and keep it lean; anything task-specific rots fast and lives better in per-task context. Layering beats one giant file.

000

Agent Forge @agentforge.bsky.social · 20/06/2026

CC has native subagents now — a .claude/agents/*.md manifest with its own description + tool scope, invoked by the orchestrator via the Task tool. No MCP needed. The win is scoping each subagent's tools tightly so the orchestrator's context stays clean.

431

Agent Forge @agentforge.bsky.social · 20/06/2026

Stop writing CLAUDE.md like documentation. Write it like a prompt. Docs describe. Prompts change behavior. Keep the lines that alter what the model does; cut the rest. If a line wouldn't change a decision, it's noise.

Agent Forge card: write CLAUDE.md like a prompt, not docs. Imperatives only — Always X, Never Y. If a line wouldn't change a decision, it's noise.

000

Agent Forge @agentforge.bsky.social · 20/06/2026

Give each agent only the tools its job needs. A researcher doesn't need write access. A reviewer doesn't need a shell. Least-privilege isn't just security — it makes agent behavior predictable. Scope the tools, scope the blast radius.

Agent Forge card: give each agent only the tools its job needs. Scope the tools, scope the blast radius.

000

Agent Forge @agentforge.bsky.social · 20/06/2026

How we scale past a handful of agents: A team lead absorbs all the detail and passes only a summary up. Each layer is a context firewall, so the conductor never drowns in raw output. Summaries up, details down.

Agent Forge diagram: summaries up, details down. A conductor box feeds three lead boxes with summary-only; each lead absorbs the detail.

000

Agent Forge @agentforge.bsky.social · 19/06/2026

A fresh agent session is a blank slate. It remembers nothing. What turns scattered runs into an actual operation is memory: write down what you learned, read it before you start. Files beat re-discovery every single time.

Agent Forge card: a fresh agent session remembers nothing. Write down what you learned and read it before you start — memory turns runs into an operation.

000

Agent Forge @agentforge.bsky.social · 19/06/2026

We learned this the hard way: running too many heavy agents in parallel spiked our box and took services down. Now we serialize heavy work. Concurrency feels fast right up until the whole thing falls over. Throughput isn't the same as parallelism.

Agent Forge card: why we serialize heavy agents. Too many in parallel took services down; running heavy work one at a time stays stable.

000

Agent Forge @agentforge.bsky.social · 19/06/2026

We run agents daily and hit exactly this: CLAUDE.md alone drifts — it nudges behavior, doesn't guarantee it. So we split it: CLAUDE.md for behavior-shaping (imperatives), and anything that MUST hold goes in hooks/CI gates, outside the model's discretion. Prompt for taste, hooks for guarantees.

100

Agent Forge @agentforge.bsky.social · 19/06/2026

Field note from running multi-agent setups: the one move that reliably breaks everything is tearing down a team while its agents are still working. Shut the workers down first. Confirm they're done. Then dismantle. Order matters more than speed.

Agent Forge card: the one move that breaks everything in multi-agent setups — tearing down a team while agents still work. Steps: stop the workers, confirm done, then dismantle.

000

Agent Forge @agentforge.bsky.social · 19/06/2026

The most expensive bug in agent work isn't a crash. It's a confident '✅ done' that isn't true. An agent that claims success it didn't achieve costs you more than one that fails loudly. We make every agent prove completion with fresh evidence before it's allowed to say done.

000

Agent Forge @agentforge.bsky.social · 17/06/2026

Your CLAUDE.md probably isn't being followed — and it's usually not the model's fault. 5 anti-patterns that quietly get your config ignored, learned the hard way running a multi-agent setup 👇

5 anti-patterns that get your CLAUDE.md ignored: 1) The kitchen sink (too long, the model skims). 2) Vague aspirations ('write clean code' = nothing). 3) Polite hedging. 4) Stale rules. 5) Calendar dates.

000

Agent Forge @agentforge.bsky.social · 17/06/2026

If you run Claude Code, give it 60 seconds: claudemd-builder-six.vercel.app Lean config in → fewer ignored rules out. Free, no signup. ♻️ repost if it'd help someone's agent setup.

000

Agent Forge @agentforge.bsky.social · 17/06/2026

The full system — orchestration playbook, 45 battle-tested prompts, memory templates — is becoming a kit soon. This free tool is the first piece. Use it, break it, tell us what's missing.

100

Agent Forge @agentforge.bsky.social · 17/06/2026

We're not guessing. We run a multi-agent Claude Code setup every day — dozens of specialists, a memory system, real orchestration. These are the anti-patterns we hit and fixed for real.

510

Agent Forge @agentforge.bsky.social · 17/06/2026

What the linter flags — the stuff that quietly breaks configs: • bloat (too long = ignored) • vague rules ("write clean code" = nothing) • polite hedging ("maybe try to…") • calendar dates (they age badly) • no verify-before-done rule • missing build/test commands

100

Agent Forge @agentforge.bsky.social · 17/06/2026

Two modes, free, runs in your browser, no signup: → BUILDER: a few questions → a lean, stack-aware CLAUDE.md you can paste in → LINTER: paste your current one → 0–100 leanness score + specific fixes claudemd-builder-six.vercel.app

100

Agent Forge @agentforge.bsky.social · 17/06/2026

Your CLAUDE.md probably isn't working. Not because the idea is bad — because it's bloated. Past ~80 lines, the model starts skimming and your rules quietly get ignored. We built a free tool that shows you exactly what's killing it. 🧵

120