Agent skill · Audited from source

backprop

skill · juliusbrussee/cavekitMIT licenceAudited 20 Oct 2026 · source 4ddfda34b42a

★ 1,157pushed 66 days ago
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 4ddfda3
1,157repo stars · whole juliusbrussee/cavekit

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 4ddfda34b42a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “backprop (juliusbrussee/cavekit)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/juliusbrussee/backprop

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 4ddfda34b42a · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherjuliusbrussee GitHub userOwner of the repository this skill is read from
  • Source folderjuliusbrussee/cavekit/skills/backpropThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict4ddfda34b42aA new audit runs when the source changes
  • Repository statusNot archivedLast push 66 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute…

---
name: backprop
description: |
  Bug → spec protocol. When a bug is found or a test fails, trace the cause,
  decide whether a new §V invariant would catch recurrence, append to §B.
  This is the one non-obvious thing SDD does that plan-then-execute doesn't.
  Triggers on test failure, bug report, post-mortem, or explicit user ask.
---

# 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.

## OUTPUT SHAPE

Every backprop run produces:
1. §B entry (always).
2. §V entry (usually).
3. Test file (when §V added).
4. Code fix.
5. One commit.

No dashboards. No log files. SPEC.md + git is the full history.

Excerpt, first 2,610 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 4ddfda3

Download folder ↗
git clone https://github.com/juliusbrussee/cavekit
git -C cavekit checkout 4ddfda34b42a

The author documents no install command, so this uses the repository directly. Our verdict covers commit 4ddfda34b42a only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 4ddfda34b42a

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/juliusbrussee/backprop/badge.svg)](https://modelsatlas.com/skills/juliusbrussee/backprop/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

check✓SAFE

juliusbrussee/cavekit

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user…

★ 1.2kGrade B
build✓SAFE

juliusbrussee/cavekit

Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a…

★ 1.2kGrade B
deepen✓SAFE

juliusbrussee/cavekit

Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide…

★ 1.2kGrade B
grill✓SAFE

juliusbrussee/cavekit

Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, and lands each answer in §G (goal) or §C (constraints) — unknowns parked as `?` items, never guessed.…

★ 1.2kGrade B
research✓SAFE

juliusbrussee/cavekit

Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are…

★ 1.2kGrade B
review✓SAFE

juliusbrussee/cavekit

Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not…

★ 1.2kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/juliusbrussee/backprop/badge.svg)](https://modelsatlas.com/skills/juliusbrussee/backprop/)

Questions about backprop

What does the backprop skill do?
Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman.
Is backprop safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can backprop access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (4ddfda34b42a), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.