late-night-regrets

late-night-regrets is a skill for Claude Code, Codex from rcarmo/piclaw-addons. It costs 31 tokens per session (871 once invoked), scanned A, original, MIT.

A nightly tool that sorts chat messages into quality categories, such as misunderstandings, corrections, or successful requests, then records reflections about recurring problems.

In plain words
What is it for?
Use it to review chat history, find cases where the agent misunderstood or under-delivered, and write notes about improvements.
Why use it?
It helps identify interaction patterns that might otherwise be missed across many conversations. Classification is done without using model tokens.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review chat history, find cases where the agent misunderstood or under-delivered, and write notes about improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rcarmo/piclaw-addons/late-night-regrets
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add rcarmo/piclaw-addons --skill late-night-regrets
Clone the repo
git clone --depth 1 https://github.com/rcarmo/piclaw-addons

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for late-night-regrets

README.md
[![agentmods](https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/late-night-regrets/github.svg)](https://agentmods.dev/skills/rcarmo/piclaw-addons/late-night-regrets)
Your own site
<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/late-night-regrets"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/late-night-regrets/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for late-night-regrets

Your own site · 80×15
<a href="https://agentmods.dev/skills/rcarmo/piclaw-addons/late-night-regrets"><img src="https://agentmods.dev/badge/skills/rcarmo/piclaw-addons/late-night-regrets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 871 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00871
Opus 5 $0.00015 $0.00436
Sonnet 5 $0.00006 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 11d ago against content hash 47c2b5a05773, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

late-night-regrets scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

addons/late-night-regrets/skills/late-night-regrets/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Late Night Regrets

A lightweight, zero-token-cost interaction-quality classifier that runs nightly to identify behavioral patterns worth improving.

What it does

  1. Trains a Multinomial Naive Bayes classifier on the full chat message history
  2. Classifies every user message that follows an agent turn into quality categories
  3. Flags attention-worthy messages (corrections, misinterpretations, under-deliveries)
  4. Triggers a short agent reflection pass that reads flagged messages, identifies patterns, and writes learnings to notes

Categories

Label Meaning
successful_execution Agent fulfilled the request correctly; user approved or moved on
course_correction User had to steer, clarify, or redirect
misinterpretation Agent misread intent; user explicitly corrected
over_engineering Agent did too much; user asked to simplify
under_delivery Agent gave too little; user pushed for more
context_failure Agent forgot/lost context; user had to repeat
good_proactive Agent anticipated a need; user approved
neutral Normal flow, no strong signal

How classification works (no model tokens)

  • Messages are tokenized (lowercased, code/URLs stripped, bigrams, structural features)
  • Sequential context features: previous message sender, length, turn-pair detection, self-repetition ratio
  • Weak labels derived from pattern matching on user follow-ups (approval words, correction phrases, repetition detection)
  • Standard MNB training with 80/20 deterministic split
  • Confidence-based filtering: only non-neutral predictions above threshold get flagged

Nightly flow

The scheduled task runs at 02:30 UTC (configurable):

1. bun run <addon>/scripts/train-interaction-quality-bayes.ts
   → retrains on full history, writes weights + predictions + attention file

2. Agent reads attention file, filters last 24h

3. For each flagged message:
   - Reads surrounding context from messages DB
   - Identifies what the user wanted vs what agent did

4. Writes patterns to notes/memory/interaction-reflections.md
   - Date, top patterns, behavioral adjustments
   
5. Appends new steering cues to notes/memory/feedback.md if warranted

Read the full file on GitHub · 97 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 97 lines · 31 tokens per session scan A 47c2b5a05773

Subscribe to this mod's changes

late-night-regrets is a skill published in the GitHub repository rcarmo/piclaw-addons (23 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 871 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.