Sync AGENTS.md

Shared instructions for Sync, a project that watches the outside APIs a codebase uses and opens pull requests when those APIs change, fail, or become costly.

In plain words
What is it for?
Use it when changing Sync's API dependency graph, detection pipeline, agents, or related project code.
Why use it?
It explains the project's purpose and constraints so code changes fit its data pipeline and do not add unnecessary processing time.

Instructions file for CodexOpenCode

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/stroland02/sync/agents-md
Clone the repo
git clone --depth 1 https://github.com/stroland02/Sync

Made for: Codex, OpenCode.

Per session 6,449 This file is loaded in full into every session.
When invoked 6,449 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.06449 $0.06449
Opus 5 $0.03224 $0.03224
Sonnet 5 $0.01290 $0.01290
Haiku 4.5 $0.00645 $0.00645

Measured yesterday against content hash a36006af14a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Sync AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

**Always pass `encoding="utf-8"` explicitly** to `read_text`, `write_text`, `open`, **and `subprocess.run(..., text=True)`**. On Windows all of these default to the locale codepage — cp1252 here — so any non-ASCII byte c
AGENTS.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync — working conventions

Read this before writing code. It is the shared context every agent working in this repository gets; briefs and plans layer on top of it, never against it.

What this project is

Sync watches the third-party APIs a codebase calls and opens verified pull requests when one of them breaks, drifts, or wastes money. Design: docs/superpowers/specs/2026-07-25-sync-self-maintaining-apis-design.md.

The load-bearing idea is the API Dependency Graph: static call sites joined against vendor changes and runtime telemetry. Detectors query it, and all of them emit one Finding type into one remediation pipeline. If you are adding something that does not read from or write to that graph, question whether it belongs.

Latency is a design constraint, not a later optimisation

docs/superpowers/specs/2026-07-25-sync-latency-architecture.md is binding on pipeline design. Read it before changing the shape of any pipeline, adding an agent, or introducing a stage.

The rule it exists to enforce: every agent must shorten the critical path or improve a result. An agent that does neither is latency and cost with extra steps.

One consequence binds everywhere, because breaking it fails silently: any state key written by parallel branches must declare a reducer. Without one, concurrent writes are dropped — no error, no warning, missing results.

Two more, both scoped to the remediation pipeline and both in .claude/rules/remediate-stage.md: the critical path is dominated by the customer's CI run, and locate → patch → verify is a data dependency rather than an ordering accident.

This is a data pipeline, and it obeys data-pipeline rules

docs/superpowers/specs/2026-07-27-sync-pipeline-discipline.md carries the argument and names what deliberately does not apply. Two of the six rules are purely about vendor adapters — keep VendorChange.raw, and a signature proves origin rather than correctness — and live in .claude/rules/signal-stage.md. The four that bind every session:

Read the full file on GitHub · 299 lines

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. yesterday First seen · 299 lines · 6,449 tokens per session scan A a36006af14a2

Subscribe to this mod's changes

Sync AGENTS.md is an instructions file published in the GitHub repository stroland02/Sync (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 6,449 tokens to every session, about $0.0322 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories