sync

sync is a command for coding agents from openplanr/planr-pipeline. It costs 59 tokens per session (426 once invoked), scanned A, original, MIT.

A command for checking whether project specifications, quick tasks, and issue-tracker items agree with one another inside `.planr/`.

In plain words
What is it for?
Use it to audit planning alignment, optionally apply safe local corrections, and optionally push updated tasks and commits to the selected issue tracker.
Why use it?
It finds missing links and predictable status mismatches between internal planning documents and work items sent to Linear or GitHub.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the planr-pipeline plugin — 8 skills, 10 commands, 9 agents, 1 hook shipped together

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 commands/openplanr/planr-pipeline/sync
Clone the repo
git clone --depth 1 https://github.com/openplanr/planr-pipeline

Or install planr-pipeline, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 9 agents, 1 hook.

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 sync

README.md
[![agentmods](https://agentmods.dev/badge/commands/openplanr/planr-pipeline/sync.svg)](https://agentmods.dev/commands/openplanr/planr-pipeline/sync)
Your own site
<a href="https://agentmods.dev/commands/openplanr/planr-pipeline/sync"><img src="https://agentmods.dev/badge/commands/openplanr/planr-pipeline/sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 426 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00059 $0.00426
Opus 5 $0.00030 $0.00213
Sonnet 5 $0.00012 $0.00085
Haiku 4.5 $0.00006 $0.00043

Measured 3d ago against content hash 79640cec2401, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sync 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 3d 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.

commands/sync.md · 26 lines

What it actually says

/planr-pipeline:sync [--apply] [--push] [--branch ] [--tracker linear|github|auto]

Read-only by default — never mutates disk or the network unless --apply / --push (or an explicit confirmation) is given. Fatals use ${CLAUDE_PLUGIN_ROOT}/procedures/fatal-error-format.md.

Execute ${CLAUDE_PLUGIN_ROOT}/procedures/sync-workflow.md — it holds the full contract (why this exists, the three links it reconciles, the seven HARD RULES, the seven Steps, and Termination). Both this command and the portable planr-sync skill read that one procedure, so the sync workflow is implemented exactly once. "Done" is evidenced, never assumed: a spec is done only when all its internal tasks are done and its ship marker shows qa_gate_status: passed.

Flags

Flag Effect Default
(none) Audit + classified report only. No writes, no network. on
--apply Apply the SAFE-class fixes locally (status flips, missing wrapper QTs). off
--push After --apply, push changed QTs to the tracker, then git commit (+ push). off
--branch <name> Branch to operate on. auto-detect
--tracker <t> Force linear / github; auto uses whatever the project configures. auto
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. 3d ago First seen · 26 lines · 59 tokens per session scan A 79640cec2401

Subscribe to this mod's changes

sync is a command published in the GitHub repository openplanr/planr-pipeline (2 stars, last pushed 29d ago), licensed MIT. It adds 59 tokens to every session and 426 once invoked, about $0.0003 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.