learning-from-corrections

learning-from-corrections is a skill for Claude Code, Codex from noemuch/bridge. It costs 92 tokens per session (2,467 once invoked), scanned A, original, MIT.

A workflow for comparing manual changes in Figma, a collaborative design application, with a previously saved design snapshot.

In plain words
What is it for?
Use it after correcting an active Figma design to record eligible learnings, flag other changes, and update the active design recipe when appropriate.
Why use it?
It helps distinguish reusable design-system improvements from hardcoded changes that need attention.

Skill for Claude CodeCodex

Part of the bridge plugin — 5 skills, 1 hook, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/noemuch/bridge/learning-from-corrections
Any agent
npx skills add noemuch/bridge --skill learning-from-corrections
Clone the repo
git clone --depth 1 https://github.com/noemuch/bridge

Made for: Claude Code, Codex.

Or install bridge, the plugin that ships this one along with the rest of its 5 skills, 1 hook, 1 MCP server.

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 learning-from-corrections

README.md
[![agentmods](https://agentmods.dev/badge/skills/noemuch/bridge/learning-from-corrections.svg)](https://agentmods.dev/skills/noemuch/bridge/learning-from-corrections)
Your own site
<a href="https://agentmods.dev/skills/noemuch/bridge/learning-from-corrections"><img src="https://agentmods.dev/badge/skills/noemuch/bridge/learning-from-corrections.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00092 $0.02467
Opus 5 $0.00046 $0.01234
Sonnet 5 $0.00018 $0.00493
Haiku 4.5 $0.00009 $0.00247

Measured 5d ago against content hash 689a10729f12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learning-from-corrections 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 5d 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.

skills/learning-from-corrections/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{{ACTIVE_RULES}}

Learning From Corrections

Overview

Closes the feedback loop from manual Figma edits back into Bridge's knowledge base. Diffs the live Figma state against the saved snapshot, classifies each correction as a LEARNING (DS-compliant → persisted) or a FLAG (hardcoded → surfaced), updates learnings.json, and auto-patches the active recipe when eligible.

When to Use

Invoke when the user:

  • says "I adjusted it", "I fixed it in Figma", "fix", "correct", or "learn from what I changed"
  • has an active CSpec in specs/active/ with a snapshot

Do NOT use if:

  • there is no active CSpec — the user should make first (use generating-figma-design)
  • the user wants to start fresh — use generating-figma-design with a new description
  • the user wants to ship — use shipping-and-archiving

Procedure

Before starting, load:

  • references/transport-adapter.md (repo-root) — for Figma state re-read
  • references/compiler-reference.md (repo-root) — for scene graph recompile (if re-executing after fix)

Prerequisites

  • Active CSpec in specs/active/ (abort if missing: "No active CSpec. Run: make <description>")
  • Snapshot file exists at specs/active/{name}-snapshot.json (abort if missing: "No snapshot found. The design must have been generated with make. Run make first.")
  • Figma MCP transport available (see references/transport-adapter.md (repo-root) Section F)

1. Load artifacts

  • Read the active CSpec from specs/active/{name}.cspec.yaml
  • Read the snapshot from specs/active/{name}-snapshot.json
  • Read existing learnings from knowledge-base/learnings.json (create empty structure if file doesn't exist)
  • Load knowledge-base/registries/variables.json for token resolution

2. Re-extract current Figma state

Run a node tree extraction script via Plugin API execution, using the rootNodeId and fileKey from the snapshot's meta.

Console transport:

figma_execute({
  code: "return (async function() { ... extraction script with rootNodeId ... })();"
})

Read the full file on GitHub · 260 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. 5d ago First seen · 260 lines · 92 tokens per session scan A 689a10729f12

Subscribe to this mod's changes

learning-from-corrections is a skill published in the GitHub repository noemuch/bridge (156 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 2,467 once invoked, about $0.0005 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

work-with-design-systems

Inspect, build, or extend Figma design systems — and optionally sync them to code. Two modes in one skill: inspect mode (read-only audits with WCAG checks, component scoring, detached instance detection, handoff docs) and build mode (creating components with variable bindings, slot-based composition, structured…

natdexterra/work-with-design-systems · 260 tokens

create-anatomy

Generate a visual anatomy annotation in Figma showing numbered markers on a component instance with an attribute table. Use when the user mentions "anatomy", "anatomy annotation", "component anatomy", "create anatomy", or wants to annotate a component's structural elements.

redongreen/uSpec · 59 tokens

create-property

Generate a visual property annotation in Figma showing each configurable property axis with component instance previews. Use when the user mentions "property", "properties", "property annotation", "create property", or wants to document a component's configurable properties visually.

redongreen/uSpec · 51 tokens

create-component-md

Generate a canonical JSON contract and a self-contained implementation Markdown specification for a Figma component covering API, structure, color, and screen-reader behavior. Reads a base.json produced by the uSpec Extract plugin, runs four read-only interpretation skills in parallel, reconciles their outputs, and…

redongreen/uSpec · 107 tokens

create-structure

Generate structure specifications documenting component dimensions, spacing, padding, and how values change across density, size, and shape variants. Use when the user mentions "structure", "structure spec", "dimensions", "spacing", "density", "sizing", or wants to document a component's dimensional properties.

redongreen/uSpec · 63 tokens

create-color

Generate color annotation specifications mapping UI elements to design tokens. Use when the user mentions "color", "color annotation", "color spec", "tokens", "design tokens", or wants to document which color tokens a component uses.

redongreen/uSpec · 48 tokens