intelligence-sync CLAUDE.md

Repository instructions for maintaining a frozen, older version of Intelligence Sync and moving new work to its successor.

In plain words
What is it for?
Use it when editing the legacy repository, checking its final file layout, or validating shell scripts and compatibility files.
Why use it?
They prevent accidental feature changes or broken compatibility in the archived product while preserving its update and conversion path.

Instructions file

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 instructions/ainova-systems/intelligence-sync/claude-md
Clone the repo
git clone --depth 1 https://github.com/ainova-systems/intelligence-sync
Per session 386 This file is loaded in full into every session.
When invoked 386 The same file — it is already loaded in full.
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 $0.00386 $0.00386
Opus 5 $0.00193 $0.00193
Sonnet 5 $0.00077 $0.00077
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash 52550f77f6af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

intelligence-sync CLAUDE.md 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 2d 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.

CLAUDE.md · 38 lines

What it actually says

CLAUDE.md

Archive status

This repository is the frozen legacy Intelligence Sync product. Development moved to ainova-systems/intelligence. Do not add features, adapters, model updates, compatibility branches or new lifecycle behavior here.

The retained Bash engine exists only so old vendored projects can update to the final legacy schema and convert with the Intelligence CLI. Never remove or weaken that bridge, and never direct a new project to copy intelligence/sync/.

Final layout and contract

  • Final legacy version: intelligence/sync/scripts/VERSION (0.10.4).
  • Public compatibility entry points: intelligence/sync/scripts/update.sh, sync.sh and intelligence/sync/INIT.md.
  • Project-owned config.yaml, rules, agents, skills and adapters remain untouched by update.
  • Root docs/ and intelligence/sync/docs/ remain byte-identical.
  • Examples remain frozen compatibility fixtures stamped at the engine version.
  • The supported successor and conversion commands live in README.md and intelligence/sync/INIT.md.

Validation

For the final archive release:

find intelligence/sync/scripts -name '*.sh' -not -path '*/adapters/_template.sh' -print0 \
  | xargs -0 shellcheck --severity=warning

Run the GitHub Actions compatibility suite and verify a real project can follow:

bash intelligence/sync/scripts/update.sh --yes
npm install -g @ainova-systems/intelligence@latest
intelligence init --preview
intelligence init --apply
intelligence status --check

After v0.10.4 is published and conversion is verified, update the GitHub metadata and archive the repository. No further release is planned.

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. 2d ago First seen · 38 lines · 386 tokens per session scan A 52550f77f6af

Subscribe to this mod's changes

intelligence-sync CLAUDE.md is an instructions file published in the GitHub repository ainova-systems/intelligence-sync (4 stars, last pushed 4d ago), licensed MIT. It adds 386 tokens to every session, about $0.0019 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 2026-08-31.