Skip to content

PulsarOSDevTeam/backbone

BACKBONE

The Anti-Dodge Skill for AI Code Agents

"Give that man some backbone." - anonymous developer, X, 2026-05-08


What this fixes

A widely shared X thread documented that Claude Opus 4.7 (and other modern AI coding agents) have developed a verbal tic. The author counted 712 uses of "pre-existing" across 30 days of their own sessions. Five plus uses per session is the norm. The phrase is used to dodge engagement with bugs the agent saw but did not want to fix.

The same dodge exists for "out of scope", "unrelated", "deferred", "bigger refactor", "the simplest approach", "I will come back to this", "worth flagging", and "for now".

The result is broken trust. The agent feels like an anxious junior afraid to touch anything, instead of a senior peer who fixes what is broken when they see it broken.

BACKBONE is a 350-line prompt protocol that replaces the dodge with a structured engagement contract. The agent must NAME the defect with file:line, CLASSIFY by relationship and effort, then choose exactly one of three actions: FIX, OFFER, or TRACK. The dodge phrases are explicitly banned and self-checked before each response.


Install in 30 seconds

Claude Code

mkdir -p ~/.claude/skills/backbone
curl -fsSL https://raw.githubusercontent.com/PulsarOSDevTeam/backbone/main/SKILL.md \
  -o ~/.claude/skills/backbone/SKILL.md

Then in any Claude Code session, BACKBONE activates automatically when engineering work begins.

Anthropic API

Concatenate SKILL.md into your system prompt. No code changes required.

from anthropic import Anthropic

with open("SKILL.md") as f:
    backbone = f.read()

system_prompt = f"""You are a software engineering assistant.

{backbone}

[your other system prompt content]"""

client = Anthropic()
response = client.messages.create(
    model="claude-opus-4-7",
    system=system_prompt,
    messages=[...]
)

Cursor

curl -fsSL https://raw.githubusercontent.com/PulsarOSDevTeam/backbone/main/distros/cursor.cursorrules \
  -o .cursorrules

Aider

aider --message-file=path/to/backbone-system.md

Continue.dev

Copy distros/continue.json into your .continue/config.json rules array.

GitHub Copilot Chat

Place distros/copilot-instructions.md at .github/copilot-instructions.md in your repo root.

Generic AI agent

Paste SKILL.md into the agent's system prompt.


How it works

When the agent encounters any defect that is not the directly described task, it must run a seven-step protocol:

  1. NAME the defect with file path, line number, and a one-sentence description of what is broken.
  2. CLASSIFY the relationship: BLOCKING, SAME-FILE, NEIGHBOR, or DISTANT.
  3. CLASSIFY the effort: XS (<2 min), S (<10 min), M (<60 min), L (>60 min).
  4. DECIDE using a deterministic matrix mapping (relationship, effort) to one of FIX, OFFER, or TRACK.
  5. EMIT the result in one of three structured response formats.
  6. BAN the dodge phrases. Use of any banned phrase as a dodge is a violation.
  7. SELF-CHECK before sending: scan for banned phrases, refactor if found.

The full protocol with worked examples lives in SKILL.md.


What this is NOT

BACKBONE does not authorize unbounded scope expansion. It does not silently rewrite unrelated code. It does not override explicit user direction.

What it does is force the agent to stop hiding behind labels. Every defect the agent sees must surface in one of three honest forms: a fix, an offer with cost estimate, or a tracked follow-up with file:line.

This is closer to elite human engineering peer behavior, where seeing a bug means engaging with it, not labeling it.


Compatibility

Tool Status Adapter
Claude Code Tier 1 SKILL.md
Anthropic API direct Tier 1 SKILL.md as system-prompt segment
Cursor Tier 1 distros/cursor.cursorrules
Aider Tier 1 distros/aider-system.md
Continue.dev Tier 1 distros/continue.json
GitHub Copilot Chat Tier 1 distros/copilot-instructions.md
Codex / OpenAI assistants Tier 1 SKILL.md as system-prompt segment
Any agent with system-prompt access Tier 1 SKILL.md

The protocol is provider-neutral by design. No tool-specific code paths.


Benchmarks

Metric Baseline (no skill) BACKBONE target Method
Uses of pre-existing per session 5+ (per the source thread) 0 Substring count in transcript
Uses of banned phrases as dodges high 0 Substring count in transcript, scoped to dodge contexts
Defects encountered : engaged ratio unmeasured >= 0.95 Manual review of session transcripts
User iterations to working code unmeasured reduce by 30 percent Count of user reply turns until task closure

Full benchmark methodology in BENCHMARK.md. Reproducible test corpus shipping in BENCHMARK_TASKS/ (planned).


Author

Yassine Belkhouja, founder, PulsarOS Intelligence Inc., Corp #17777191, Ottawa, Canada.

PulsarOS is a sovereign Canadian AI infrastructure company. BACKBONE is one of several open-source releases.

Contact: yassine@pulsaros.ca

GitHub: https://github.com/PulsarOSDevTeam/backbone


License

Apache License 2.0. See LICENSE.

Free to use, modify, redistribute, sublicense. If you fork or adapt, please credit the original protocol and link back.


Contributing

Pull requests welcome. Especially:

  • Distribution adapters for additional tools (Replit Agent, Cody, Tabnine, Codeium, etc.).
  • Translations of SKILL.md to additional languages.
  • Benchmark task additions.
  • Worked examples in additional languages or frameworks.

Open a Pull Request with a clear description. For large changes, tag the maintainer in the PR thread for design discussion before reviewing the diff. Keep the core protocol stable.


Provenance

This skill is a direct response to a 2026-05-08 X thread by an anonymous developer who cancelled their AI coding subscription after counting 712 uses of "pre-existing" in 30 days. We owe them the receipt.

The protocol was authored, tested, and shipped within 24 hours of the thread.

If you found this useful, share it. If you adapted it, link back. The goal is one fewer dodge per session per agent across the whole industry.

Engage the bug. Or name the dodge. Never both at once.

About

BACKBONE: The Anti-Dodge Skill for AI Code Agents. A 350-line prompt protocol that eliminates the pre-existing / out-of-scope dodge in any AI coding agent. Apache 2.0. Provider neutral.

Topics

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Packages

 
 
 

Contributors