Kensei

context engineer

[Kensei @0xKense1]

https://t.co/WUk7rWCYuZ

[Kensei @0xKense1]

@ajs6888 you are totally right

[Kensei @0xKense1]

Daisy Hollman, an engineer on the Claude Code team, at Code with Claude: "The fastest way to make your agent better at your code base isn't a smarter model, it's a tighter feedback loop."

Her idea is red squigglies for agents: a hook that nudges Claude at the moment of the mistake, and that Claude can override when it knows better.

· 00:00 - everything you customize is just text files
· 00:23 - what an IDE for Claude looks like
· 01:36 - red squigglies for agents
· 02:12 - PostToolUse hooks
· 02:38 - the generated-file example
· 03:18 - a tighter feedback loop
· 03:48 - tools that scale with intelligence

I used a hook the other way, as a hard block on network calls. It stopped all 33 runs that went for the network, and the agents almost never looked for another way around it.

Wall or nudge: which one are your hooks?

[Kensei @0xKense1]

https://t.co/WUk7rWCYuZ

[Kensei @0xKense1]

@Charlie01748449 think same

[Kensei @0xKense1]

@0xMorlex great to hear that

[Kensei @0xKense1]

@eth_ansh hilarious

[Kensei @0xKense1]

Daisy Hollman, an engineer on the Claude Code team, at Code with Claude: "The fastest way to make your agent better at your code base isn't a smarter model, it's a tighter feedback loop."

Her idea is red squigglies for agents: a hook that nudges Claude at the moment of the mistake, and that Claude can override when it knows better.

· 00:00 - everything you customize is just text files
· 00:23 - what an IDE for Claude looks like
· 01:36 - red squigglies for agents
· 02:12 - PostToolUse hooks
· 02:38 - the generated-file example
· 03:18 - a tighter feedback loop
· 03:48 - tools that scale with intelligence

I used a hook the other way, as a hard block on network calls. It stopped all 33 runs that went for the network, and the agents almost never looked for another way around it.

Wall or nudge: which one are your hooks?

[Kensei @0xKense1]

@talemi appreciate it, did that because I understand that a lot of people are not even aware of those tips, and this could help them

[Kensei @0xKense1]

Daisy Hollman, an engineer on the Claude Code team and once a chair on the C++ committee, spent 20 minutes at Code with Claude on where your Claude Code tokens actually go.

Her rule for the context window: "Don't pay for what you don't use."

· 00:00 - the context window is a box
· 02:03 - npm on an Arduino
· 03:43 - the KV cache: change something early, pay 10x for the rest
· 06:42 - MCP: 20 servers x 15 tools fill the prompt
· 11:50 - skills: the description is always loaded
· 14:20 - hooks: zero token cost until they fire
· 17:02 - subagents
· 18:38 - why plugins can't ship a CLAUDE.md

Her CLAUDE.md point matches my test: 16 KB of rules in CLAUDE.md cost 46% more tokens per question, and the same rules in a skill cost 31% less. In my setup a bare "ok" already costs 19,100 tokens.

How much does your setup load before you type anything?

[Kensei @0xKense1]

https://t.co/WUk7rWCYuZ

[Kensei @0xKense1]

@daniel_mac8 Thx mate, appreciate it, did really hard research

[Kensei @0xKense1]

@AlexWithAi_ same lol. what eased mine: in my tests about half the runs with no rule tried to go online on their own, and a single hook blocked 33 of 33. so now auto mode only runs with that hook on. you on auto or full yolo?

[Kensei @0xKense1]

The Claude Code team explains in 7 minutes how Anthropic runs its own agents safely

Simon Willison: "I still mostly run Claude Code in YOLO mode and feel incredibly guilty about it."

· 00:11 - the YOLO mode confession
· 00:33 - almost everyone at Anthropic uses auto mode
· 00:45 - thousands of evals and hired red teamers
· 01:27 - "It doesn't catch 100% of things"
· 01:50 - a Sonnet classifier checks every bash call
· 02:42 - when a network request tries to leave the sandbox
· 04:07 - why you shouldn't build your own AI Slackbot
· 05:05 - giving Claude its own credentials
· 06:07 - credentials the agent can use but never see

The interesting part: even the team that built auto mode says it doesn't catch everything.

So I tested my own setup: 600 Claude Code runs and the 4 layers that stopped every attempt.

[Kensei @0xKense1]

https://t.co/JGPa3emUtl

[Kensei @0xKense1]

The built-in general-purpose one, Claude picked it on its own in 10 of 10 runs. The work copy had no CLAUDE.md, so the only setup each worker repeated was the skills list (30 skills). Delegating cost about 45k tokens on the task call and saved about 54k on the follow-ups, so it came out near zero. A leaner worker could tip that, worth its own run. How much did it save you per call?

[Kensei @0xKense1]

Hitting your Claude Code limit is mostly a skill issue.

I measured 12 popular tips on 945 runs. 5 of them saved nothing: subagents, the caveman skill, deny rules, turning off MCP servers, effort low on Sonnet.

The 7 that held up fit on one page. Skip #1 and you pay almost 5x for the same answer:
1. /clear between unrelated tasks: -79%
2. /compact on the same task: -60%
3. long rules in a skill, not CLAUDE.md: -31%
4. effort low on Opus: -17%
5. a flat notes map: -32%, but 18/20 right
6. naming the file: 20/20 right vs 8/20
7. Haiku for lookups: about 12x cheaper

Score yourself: how many of the 7 do you already do?

[Kensei @0xKense1]

https://t.co/WUk7rWCYuZ

[Kensei @0xKense1]

@0xMorlex try it best

[Kensei @0xKense1]

Hitting your Claude Code limit is mostly a skill issue.

I measured 12 popular tips on 945 runs. 5 of them saved nothing: subagents, the caveman skill, deny rules, turning off MCP servers, effort low on Sonnet.

The 7 that held up fit on one page. Skip #1 and you pay almost 5x for the same answer:
1. /clear between unrelated tasks: -79%
2. /compact on the same task: -60%
3. long rules in a skill, not CLAUDE.md: -31%
4. effort low on Opus: -17%
5. a flat notes map: -32%, but 18/20 right
6. naming the file: 20/20 right vs 8/20
7. Haiku for lookups: about 12x cheaper

Score yourself: how many of the 7 do you already do?

[Kensei @0xKense1]

@0xObservix thx

[Kensei @0xKense1]

The Claude Code team explains in 3 minutes why your CLAUDE.md is probably too long

Thariq Shihipar on Peter Yang's Behind the Craft: "when you say never, you don't really mean never, you just mean like most of the time, don't do this."

The team cut Claude Code's own system prompt by 80%. I measured what a long CLAUDE.md costs you, 20 runs per setup on Sonnet 5.5:
- 16 KB of unrelated rules in CLAUDE.md: +46% tokens per question
- the same rules moved into a skill: 31% fewer tokens

00:25 why they cut the prompt by 80%
01:15 why "never" in a rule rarely means never
01:28 trim your CLAUDE.md and your skills
01:43 what about MCP servers

My take: half the NEVERs in a CLAUDE.md are there to calm us down, not to guide the model.

Mine had 24. How many are in yours?

[Kensei @0xKense1]

https://t.co/WUk7rWCYuZ

[Kensei @0xKense1]

@de1lymoon glad you liked it

[Kensei @0xKense1]

@ClaudeDevs 90% written by Claude, reverts down 40%. turns out the bugs were mostly mine

[Kensei @0xKense1]

The Claude Code team explains in 3 minutes why your CLAUDE.md is probably too long

Thariq Shihipar on Peter Yang's Behind the Craft: "when you say never, you don't really mean never, you just mean like most of the time, don't do this."

The team cut Claude Code's own system prompt by 80%. I measured what a long CLAUDE.md costs you, 20 runs per setup on Sonnet 5.5:
- 16 KB of unrelated rules in CLAUDE.md: +46% tokens per question
- the same rules moved into a skill: 31% fewer tokens

00:25 why they cut the prompt by 80%
01:15 why "never" in a rule rarely means never
01:28 trim your CLAUDE.md and your skills
01:43 what about MCP servers

My take: half the NEVERs in a CLAUDE.md are there to calm us down, not to guide the model.

Mine had 24. How many are in yours?

[Kensei @0xKense1]

@talemi happy you liked it, hope it helps

[Kensei @0xKense1]

https://t.co/WUk7rWCYuZ