learn-from-correction

learn-from-correction is a skill for Claude Code, Codex from assafkip/kipi-system. It costs 45 tokens per session (2,060 once invoked), scanned A, original, MIT.

A method for turning a correction pair—the agent's output and the human's actual correction—into a proposed improvement to a skill or persona file. It produces a proposal for review instead of editing the target directly.

In plain words
What is it for?
Use it after reviewing or rewriting agent work to suggest a general principle that could prevent similar mistakes in the future.
Why use it?
It helps preserve lessons from repeated corrections without turning one example into a brittle list of rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 q-system/.q-system/scripts/correction_outcome.py <memory_id> <session_id>.

Part of the kipi-core plugin — 10 skills, 7 commands shipped together

Good fit Use it after reviewing or rewriting agent work to suggest a general principle that could prevent similar mistakes in the future.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/assafkip/kipi-system
agentmods
npx agentmods add skills/assafkip/kipi-system/learn-from-correction

Made for: Claude Code, Codex.

Or install kipi-core, the plugin that ships this one along with the rest of its 10 skills, 7 commands.

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 learn-from-correction

README.md
[![agentmods](https://agentmods.dev/badge/skills/assafkip/kipi-system/learn-from-correction/github.svg)](https://agentmods.dev/skills/assafkip/kipi-system/learn-from-correction)
Your own site
<a href="https://agentmods.dev/skills/assafkip/kipi-system/learn-from-correction"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/learn-from-correction/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 learn-from-correction

Your own site · 80×15
<a href="https://agentmods.dev/skills/assafkip/kipi-system/learn-from-correction"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/learn-from-correction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,060 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 172
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00045 $0.02060
Opus 5 $0.00023 $0.01030
Sonnet 5 $0.00009 $0.00412
Haiku 4.5 $0.00005 $0.00206

Measured 9d ago against content hash 9fe953220c45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

learn-from-correction 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 9d 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.

plugins/kipi-core/skills/learn-from-correction/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn From Correction

You take a correction (what an agent proposed vs. what the human actually did) and propose a principle edit to the skill/persona file that should have caught it. The proposal goes to q-system/output/skill-proposals/ for the founder to review and merge through normal git flow.

This skill exists because the best prompt today is not the best prompt a month from now. Corrections the founder is already making (rewrites of agent drafts, anti-pattern additions to Skeptic, copy edits) carry the signal needed to keep skills sharp - but only if something captures that signal as a durable principle.

Before writing anything, read references/principle-vs-rule.md. The guardrails there are load-bearing: principles transfer, rules overfit. A correction turned into a rule produces a brittle decision tree. The same correction turned into a principle reshapes how the agent reasons.

Constraints (ENFORCED)

  • Never edit the target skill file directly. Output is always a proposal markdown in q-system/output/skill-proposals/. The founder reviews, edits, and merges via normal git flow so Codex review fires on the diff (same gate as any other code change).
  • One correction at a time. If the founder hands you a batch of corrections, process them sequentially. Each one gets its own proposal file or its own section. Do not bundle unrelated corrections into one principle.
  • Always include the source correction in the proposal. The founder needs to verify your interpretation. Quote the agent output, the human output, and your inferred diff.
  • If the correction does not generalize, say so. Not every correction maps to a missing principle. Some are one-off context. The honest answer is sometimes: "this is a one-off, no principle change recommended."

Read the full file on GitHub · 173 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 173 lines · 45 tokens per session scan A 9fe953220c45

Subscribe to this mod's changes

learn-from-correction is a skill published in the GitHub repository assafkip/kipi-system (110 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,060 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.

Related

Other skills, from other repositories

core

This skill should be used when the user says "capture memory", "save to memory", "remember this", or trigger phrases like: "I've decided", "let's use", "we're going with", "I learned", "turns out", "TIL", "discovered", "I'm stuck", "blocked by", "always use", "never do", "convention is". Also triggers on recall…

modeled-information-format/mnemonic · 109 tokens

blackboard

Cross-session handoff, persistent context via blackboard, and agent coordination patterns.

modeled-information-format/mnemonic · 18 tokens

custodian

Memory system custodian for health checks, validation, and maintenance. Trigger phrases: "check memory health", "validate memories", "fix broken links", "update decay", "relocate memories", "audit memories", "memory maintenance", "custodian", "memory health".

modeled-information-format/mnemonic · 58 tokens

format

MIF Level 3 specification, memory templates, and formatting guidelines.

modeled-information-format/mnemonic · 15 tokens

ontology

Ontology-based entity discovery and validation for mnemonic memories. Define custom namespaces, entity types, traits, and relationships. Triggers: "entity discovery", "validate ontology", "define namespaces", "resolve entity references", "list ontologies", "show namespaces", "entity types", "entity relationships"…

modeled-information-format/mnemonic · 74 tokens

search

This skill should be used when the user says "search memories", "find in memories", "grep mnemonic", "look for memory", "deep search", "synthesize knowledge", or asks questions like "what do we know about X". Provides progressive disclosure and enhanced iterative search with synthesis.

modeled-information-format/mnemonic · 60 tokens