agentleFS
imMamdouhaboammarimMamdouhaboammar/anti-slop-engineering/skills/backprop-guard/SKILL.md

backprop-guard

Skill4 starsChanged 31 days agoMITView on GitHub

Backpropagate downstream code failures, test rejections, and slop findings into upstream rules, invariants, and AGENTS.md rather than merely patching downstream symptoms.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When an AI coding assistant introduces a bug or writes slop, standard workflows only fix the local file.

    line 16
  2. Distinctive:

    Atomically Apply: Update the invariant ledger so all future agent turns ingest the new constraint at Gate 0.

    line 22
  3. Distinctive:

    One Canonical Owner: Every backpropagated lesson belongs in exactly one Single Source of Truth (SSOT).

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Upstream Invariant & Rule Backpropagation Guard

Feed errors from output back through the generative layers that produced them, updating upstream invariants so the failure can never recur.

Why This Skill Is Needed & Target State

When an AI coding assistant introduces a bug or writes slop, standard workflows only fix the local file. The prompt, rules, constitution, or missing invariant that permitted the mistake remain untouched. Consequently, subsequent sessions repeat the exact same failure.

The target state is an error backpropagation pipeline:

  1. Identify the Symptom: Map the failure to its error class (DEMOCK, MANDELA, REDUCTION, AST_SLOP, SRE_KISS).
  2. Question Upstream Requirements (Elon Step 1): Challenge why the rule or gap existed.
  3. Pin the SSOT Owner: Direct the invariant into AGENTS.md, .anti-slop/invariant-ledger.json, or a specific skill file.
  4. Atomically Apply: Update the invariant ledger so all future agent turns ingest the new constraint at Gate 0.

Invariant Rules

  1. Backprop Before Local Merge: Significant downstream failures must emit an upstream invariant candidate before PR completion.
  2. One Canonical Owner: Every backpropagated lesson belongs in exactly one Single Source of Truth (SSOT).
  3. Preserve Generalization: Formulate rules as general behavioral constraints, not hyper-narrow one-off exceptions.

CLI Usage

# Generate backprop record for an observed finding
bunx anti-slop-engineering backprop \
  --finding DEMOCK_SILENT_FALLBACK \
  --file "src/db/client.ts" \
  --line 42 \
  --excerpt "catch { return []; }" \
  --json

# Atomically commit invariant to .anti-slop/invariant-ledger.json
bunx anti-slop-engineering backprop \
  --finding DEMOCK_SILENT_FALLBACK \
  --file "src/db/client.ts" \
  --line 42 \
  --excerpt "catch { return []; }" \
  --apply

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.