backprop

backprop is a skill for Claude Code, Codex from JuliusBrussee/cavekit. It costs 76 tokens per session (730 once invoked), scanned A, original, MIT.

A process for turning a bug or failed test into a lasting software-specification rule.

In plain words
What is it for?
Tracing failures to their cause, updating the specification, adding a test, and recording the bug and its prevention after incidents or failed checks.
Why use it?
Fixing code alone may leave the same class of bug able to return. This process adds a checkable rule and a test aimed at preventing recurrence.

Skill for Claude CodeCodex

Part of the ck plugin — 8 skills, 7 commands 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/juliusbrussee/cavekit/backprop
Any agent
npx skills add JuliusBrussee/cavekit --skill backprop
Clone the repo
git clone --depth 1 https://github.com/JuliusBrussee/cavekit

Made for: Claude Code, Codex.

Or install ck, the plugin that ships this one along with the rest of its 8 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 backprop

README.md
[![agentmods](https://agentmods.dev/badge/skills/juliusbrussee/cavekit/backprop.svg)](https://agentmods.dev/skills/juliusbrussee/cavekit/backprop)
Your own site
<a href="https://agentmods.dev/skills/juliusbrussee/cavekit/backprop"><img src="https://agentmods.dev/badge/skills/juliusbrussee/cavekit/backprop.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 730 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 $0.00076 $0.00730
Opus 5 $0.00038 $0.00365
Sonnet 5 $0.00015 $0.00146
Haiku 4.5 $0.00008 $0.00073

Measured 3d ago against content hash 35eb93f05ef6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backprop 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 3d 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/backprop/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

backprop — bug → spec

Plan-then-execute fixes the code & forgets. SDD fixes the code AND edits spec so recurrence is impossible. That edit is backprop.

WHEN TO BACKPROP

  • Test failed at /build verification.
  • User reports bug.
  • Post-mortem after production incident.
  • /check flags VIOLATE with root cause found.

SIX STEPS

1. TRACE

Read failure output / bug report. Find exact file:line of wrong behavior. Name root cause in one caveman sentence.

2. ANALYZE

Ask three questions:

  • Would a new §V invariant catch this class of bug? (most common: yes)
  • Is §I wrong — did spec claim shape the code cannot deliver? (sometimes)
  • Is §T wrong — did we build the wrong thing? (rare but real)

3. PROPOSE

Draft the spec change. Never skip §B; §V/§I/§T are case-by-case.

Template:

§B row: B<next>|<date>|<root cause>|V<N>
§V line: V<next>: <testable rule that would have caught it>

Example:

§B row: B3|2026-04-20|refund job ran twice on retry|V7
§V line: V7: ∀ refund → idempotency key check before charge reversal

4. GENERATE TEST

New invariant without test = lie. Add failing test first. Name test so it cites the invariant: TestV7_RefundIdempotent.

5. VERIFY

Fix code. Run test. Must pass. Run full suite. Must not regress.

6. LOG

Commit spec edit + test + code fix together. Commit msg: backprop §B.<n> + §V.<N>: <one-line cause>.

WHAT MAKES A GOOD INVARIANT

  • Testable in code (grep-able or assert-able).
  • Scoped to a behavior, not a file.
  • Stated positively when possible (! hold over ⊥ forbid).
  • References §I surface where it applies.

Bad: V8: code should be correct. Good: V8: ∀ pg_query ! params interpolated via driver, ⊥ string concat.

WHEN NOT TO ADD §V

  • Bug was purely mechanical typo with no class (i++ vs i-- in throwaway).
  • Fix is a one-time migration.
  • Root cause is external dep (upgrade deps instead, note in §C).

Still append §B entry — record that this failure mode was considered. Future bug with same smell → §B search shows precedent.

Read the full file on GitHub · 90 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. 3d ago First seen · 90 lines · 76 tokens per session scan A 35eb93f05ef6

Subscribe to this mod's changes

backprop is a skill published in the GitHub repository JuliusBrussee/cavekit (1,141 stars, last pushed 19d ago), licensed MIT. It adds 76 tokens to every session and 730 once invoked, about $0.0004 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

build-executor

Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.

MageByte-Zero/spec-superflow · 39 tokens

workflow-start

Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…

MageByte-Zero/spec-superflow · 125 tokens

release-archivist

Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.

MageByte-Zero/spec-superflow · 42 tokens

bug-investigator

Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.

MageByte-Zero/spec-superflow · 37 tokens

spec-writer

Create or refine spec-superflow planning artifacts. Invoke when the change is understood well enough to write proposal.md, specs/, design.md, and tasks.md.

MageByte-Zero/spec-superflow · 35 tokens

contract-builder

Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.

MageByte-Zero/spec-superflow · 39 tokens