Hear your agent suffer through your code

tpoindex 24 minutes ago | parent | next [-]

Marvelous!

Next innovation in this space should be the robotic arm that issues a dope-slap to the developer for writing crappy/buggy/insecure code.

	▲	joshmarlow 11 minutes ago \| parent \| next [-]
		I propose a claude skill to email glitter bombs where appropriate.
	▲	Mithriil 13 minutes ago \| parent \| prev [-]
		Add the feature of doing a high five for the rare cases when it's actually good.

▲

fredley 3 hours ago | parent | prev | next [-]

I need a version of this which swears loudly when an assumption it made turns out to be wrong, with the volume/passion/verbosity correlated with how many tokens it's burned on the incorrect approach.

▲

shivaniShimpi_ 3 hours ago | parent | next [-]

i didnt realize i needed the volume scaling with tokens burned as much as i do now xD imagine the screaming when it confidently refactors something for 40k tokens and then finds out the thing it deleted was load bearing

	▲	ben30 2 hours ago \| parent \| next [-]
		I have in my agents file “Chesterton’s fence” as pointer to think carefully before you remove something
	▲	vasco 2 hours ago \| parent \| prev [-]
		I have general reviewer named Feynman with his personality that shits on anything other agents do and sends it back before it hits me and it sounds perfect to include some sound bites from YouTube clips. Great idea!!

▲

amelius 16 minutes ago | parent | prev | next [-]

I want a version that I can punish.

▲

whattheheckheck 26 minutes ago | parent | prev [-]

Now you know the feeling of VP when the team says they need to refactor stuff

▲

deathlock 39 minutes ago | parent | prev | next [-]

Any chance you could add a video showcasing the plugin? I don't have any agentic app but I would love to see an example of what it does!

▲

x187463 18 minutes ago | parent | prev | next [-]

From a quick look, this doesn't have the model evaluate code quality, but it runs a heuristic analysis script over the code to determine the groan signal. Did I miss something? Why not leave it to the model to decide the quality of the code?

	▲	isolay 9 minutes ago \| parent [-]
		You unlock this feature by subscribing to the Premium Gold plan.

▲

rob74 an hour ago | parent | prev | next [-]

I wish the agents could hear me when I have to suffer through their code!

	▲	isolay 5 minutes ago \| parent [-]
		And then what? Their gigahertz machine hearts will skip a beat out of empathy?

▲

AndrewVos 3 hours ago | parent | prev | next [-]

Hi Hacker News, I'm Andrew, the CTO of Endless Toil.

Endless Toil is building the emotional observability layer for AI-assisted software development.

As engineering teams adopt coding agents, the next challenge is understanding not just what agents produce, but how the codebase feels to work inside. Endless Toil gives developers a real-time signal for complexity, maintainability, and architectural strain by translating code quality into escalating human audio feedback.

We are currently preparing our pre-seed round and speaking with early-stage investors who are excited about developer tools, agentic engineering workflows, and the future of AI-native software teams.

If you are investing in the next generation of software infrastructure, we would love to talk.

	▲	vermilingua 21 minutes ago \| parent [-]
		Missed it by 24 days.

▲

tuo-lei an hour ago | parent | prev | next [-]

the scan catches surface stuff. funnier signal would be tracking when the agent reads the same file 3 times in a row, or deletes what it just wrote. you can hear the frustration in the access pattern.

▲

AndreVitorio 3 hours ago | parent | prev | next [-]

This desperately needs a demo video in the repo.

	▲	shivaniShimpi_ 3 hours ago \| parent [-]
		hear hear!!!

▲

lorenzohess 2 hours ago | parent | prev | next [-]

Please add Minecraft hurt sound effects for when my project fails to build, linter fails, segfault, etc

	▲	automatic6131 an hour ago \| parent [-]
		We could have the roblox oof but then there'd be the possibility of giving (a certain) amateur world backgammon championship participant money

▲

esperent 3 hours ago | parent | prev | next [-]

I tried it but all I hear is a choir of angels, is it broken?

	▲	medwezys 3 hours ago \| parent \| next [-]
		I guess you’re working on a greenfield project?
	▲	AndrewVos 3 hours ago \| parent \| prev [-]
		Actually, that's not a bad idea!

▲

8-prime 3 hours ago | parent | prev | next [-]

Does this actually relate to the code quality being observed by the agent? The readme isn't very clear on that IMO. I have some projects I'd love to try this out on, but only if I am to get an accurate representation of the LLMs suffering.

▲

CWwdcdk7h 3 hours ago | parent | next [-]

https://github.com/AndrewVos/endless-toil/blob/main/plugins/...

So it is left up to agent to decide.

	▲	Ghoelian 3 hours ago \| parent [-]
		The agent is instructed to execute this Python script: https://github.com/AndrewVos/endless-toil/blob/main/plugins/... So looks like it's mainly looking for FIXME/TODO etc comments, deep nesting, large files, broad catches, stuff like that.

▲

AndrewVos 3 hours ago | parent | prev [-]

I'm very open to suggestions, but currently it's a very simple scan of the code. Check the python scripts.

▲

greg_dc 3 hours ago | parent | prev | next [-]

Honestly, I don't care about Opus 4.7. This is the true evolution of agentic coding.

▲

coldcity_again 3 hours ago | parent | prev | next [-]

I really want this! Any chance of a Cursor version?

	▲	AndrewVos 3 hours ago \| parent [-]
		I just added a cursor plugin to the repo, let me know how it goes!

▲

philipwhiuk an hour ago | parent | prev [-]

https://github.com/AndrewVos/endless-toil/blob/main/plugins/... relevant bit