semantic-backprop-attributor

semantic-backprop-attributor is a skill for Claude Code, Codex from AnthonyAlcaraz/agentic-graph-rag-skills. It costs 183 tokens per session (2,602 once invoked), scanned A, original, MIT.

A method for tracing an agent-system failure back through the execution graph to the component that caused it, then sending precise textual feedback to that component and its connected neighbors.

In plain words
What is it for?
Use it in self-evolving agent systems to assign responsibility for failures and generate context-aware feedback based on the outputs and errors of connected components.
Why use it?
It helps prevent a fix to one part of a multi-step system from creating hidden failures elsewhere.

Skill for Claude CodeCodex

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

Good fit Use it in self-evolving agent systems to assign responsibility for failures and generate context-aware feedback based on the outputs and errors of connected components.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor
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 AnthonyAlcaraz/agentic-graph-rag-skills --skill semantic-backprop-attributor
Clone the repo
git clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skills

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 semantic-backprop-attributor

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor/github.svg)](https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor)
Your own site
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor/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 semantic-backprop-attributor

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/semantic-backprop-attributor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,602 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.
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 $0.00183 $0.02602
Opus 5 $0.00092 $0.01301
Sonnet 5 $0.00037 $0.00520
Haiku 4.5 $0.00018 $0.00260

Measured 11d ago against content hash 1c5fae8aaebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

semantic-backprop-attributor 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.

The scan reads SKILL.md. This mod also ships 2 executable files (cli.py, lib.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/self-evolution/semantic-backprop-attributor/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Backpropagation Attributor

Overview

Agents are graphs, not pipelines. The dangerous failure mode in a self-evolving system is not a bad update. It is a good update to one node that silently breaks another. In a deeply interconnected graph, improving a component in isolation causes "action at a distance" failures that are hard to trace. Semantic backpropagation is the mechanism that prevents this.

The idea adapts the chain rule. In numerical backpropagation, gradients flow backward through a computational graph, updating each parameter by how it contributed to the loss. Semantic backpropagation does the same in natural language: the gradient is a structured description of the required change, and it flows backward through the execution graph from the point of failure.

Neighbor-awareness is the decisive part. When generating feedback for node v based on what successor w needed, the feedback includes not just v's output and w's error but the outputs of ALL OTHER predecessors of w. That context is what makes the feedback precise.

The chapter's concrete example: an Extractor pulls "Revenue: $10M", a CurrencyConverter converts it to "EUR 9.5M", and a Validator (which also received a DateChecker's "Date: 2022") flags that the exchange rate was 0.9, not 0.95. Without neighbor context, feedback to the Extractor reads "your $10M led to a conversion error" and the Extractor might wrongly change its extraction. With neighbor context, the error is correctly assigned to the CurrencyConverter's rate lookup and the Extractor is left unchanged. the neighbor-aware feedback example shows the same shape for a DevOps CausalAttributionNode, with ChangelogRetrieval and KnowledgeGraphQuery as the neighbor predecessors.

Honesty note on the metaphor: "backpropagation" here is an analogy, not a mechanism. A numerical gradient is exact and deterministic; this skill's "gradient" is credit assignment produced by LLM judgment over the execution graph — structured, neighbor-aware, and far better than unstructured blame, but still a hypothesis about causality, not a derivative. Treat every attribution as a claim to verify (rerun the trace with the blamed node patched) before committing an intervention on it. What IS deterministic in this skill: the graph traversal, the neighbor-context assembly, and the routing of the verdict.

Read the full file on GitHub · 182 lines

Files

What ships with it

2 files 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. 11d ago First seen · 182 lines · 183 tokens per session scan A 1c5fae8aaebe

Subscribe to this mod's changes

semantic-backprop-attributor is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 183 tokens to every session and 2,602 once invoked, about $0.0009 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 2026-08-31.

Related

Other skills, from other repositories

potpie-cli

Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.

potpie-ai/potpie · 50 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens

cvm-ai-doctor

A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.

TencentCloud/Octop · 60 tokens

ai-discover

Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…

kirodotdev/KiroCrew · 75 tokens

quality-hooks

Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.

a5c-ai/babysitter · 53 tokens

debug

Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.

agentic-community/mcp-gateway-registry · 45 tokens