principle-pre-image-first

principle-pre-image-first is a skill for Claude Code, Codex from bostonaholic/team. It costs 22 tokens per session (173 once invoked), scanned A, original, MIT.

A safety rule for destructive changes and rewritten history. Before changing anything, it records the original state and a way to recover it.

In plain words
What is it for?
Use it before overwriting files or content, rewriting Git history, closing records, or performing other hard-to-undo operations.
Why use it?
It lets you distinguish an existing failure from a newly introduced one and gives you a recovery point if the operation goes wrong.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also agents/openai.yaml present.

Part of the team plugin — 92 skills, 13 agents, 2 hooks shipped together

Good fit Use it before overwriting files or content, rewriting Git history, closing records, or performing other hard-to-undo operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bostonaholic/team/principle-pre-image-first
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 bostonaholic/team --skill principle-pre-image-first
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 92 skills, 13 agents, 2 hooks.

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 principle-pre-image-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/principle-pre-image-first/github.svg)](https://agentmods.dev/skills/bostonaholic/team/principle-pre-image-first)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/principle-pre-image-first"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/principle-pre-image-first/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 principle-pre-image-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/bostonaholic/team/principle-pre-image-first"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/principle-pre-image-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 173 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 $0.00022 $0.00173
Opus 5 $0.00011 $0.00086
Sonnet 5 $0.00004 $0.00035
Haiku 4.5 $0.00002 $0.00017

Measured 4d ago against content hash 4956a1d0c5a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

principle-pre-image-first 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 4d 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/principle-pre-image-first/SKILL.md · 17 lines

What it actually says

Pre-image First

Before mutation, capture the untouched baseline and a recovery anchor or pre-image; No pre-image, no destructive write.

  • Run checks BEFORE the operation so later failures classify as pre-existing or introduced.
  • Capture the recovery anchor before rewrites and report it on success and failure; preserve git reset --hard <sha> recovery where applicable.
  • Cache bodies before composing replacements for rewrite, close, or overwrite operations.
  • Compare the target with its pre-image at write time; skip and report drift.
  • Apply principle-idempotent-reruns to this comparison on re-run.
  • A baseline that could not run is UNKNOWN and never proves preservation.
Files

What ships with it

1 file 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. 4d ago Changed · -15 lines · -24 tokens per session 4956a1d0c5a1
  2. 6d ago First seen · 32 lines · 46 tokens per session scan A 0126a89ad009

Subscribe to this mod's changes

principle-pre-image-first is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 173 once invoked, about $0.0001 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 2026-09-03.