speckit.specrew-speckit.sync-retro

speckit.specrew-speckit.sync-retro is a command for Claude Code from alonf/specrew. It costs 10 tokens per session (592 once invoked), scanned A, a copy of speckit.specrew-speckit.sync-clarify, MIT.

A command that records that retrospective work has reached its workflow boundary. A retrospective is a review of what happened during an iteration and what should change next.

In plain words
What is it for?
Use it after retrospective work to record the feature and iteration, create the pending approval record, and stop when synchronization or earlier approval checks fail.
Why use it?
It keeps the saved workflow state aligned with committed retrospective documents and prevents advancement without the required gate record.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it after retrospective work to record the feature and iteration, create the pending approval record, and stop when synchronization or earlier approval checks fail.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/alonf/specrew/speckit.specrew-speckit.sync-retro
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.

Clone the repo
git clone --depth 1 https://github.com/alonf/specrew

Made for: Claude Code.

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 speckit.specrew-speckit.sync-retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/alonf/specrew/speckit.specrew-speckit.sync-retro.svg)](https://agentmods.dev/commands/alonf/specrew/speckit.specrew-speckit.sync-retro)
Your own site
<a href="https://agentmods.dev/commands/alonf/specrew/speckit.specrew-speckit.sync-retro"><img src="https://agentmods.dev/badge/commands/alonf/specrew/speckit.specrew-speckit.sync-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 592 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 83% copy Near-identical to another mod 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 $0.00010 $0.00592
Opus 5 $0.00005 $0.00296
Sonnet 5 $0.00002 $0.00118
Haiku 4.5 $0.00001 $0.00059

Measured 5d ago against content hash d94e14186bf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

speckit.specrew-speckit.sync-retro 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 5d 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.

Origin

This is a copy

83% identical to speckit.specrew-speckit.sync-clarify — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.specify/extensions/specrew-speckit/commands/speckit.specrew-speckit.sync-retro.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sync Retro Boundary State

Record the arrival (before the advancement gate)

After retro artifacts are committed to the feature branch, record the boundary arrival FIRST — the sync mints the pending crossing and writes .specrew/runtime/pending-verdict-stop.md, the controller truth the verdict stop renders from (DRIFT-198-I011-012: gating before the sync left the stop with no artifact, the marker-invention precondition):

$featureJson = Get-Content -LiteralPath .\.specify\feature.json -Raw -Encoding UTF8 | ConvertFrom-Json
$featureRef = Split-Path -Leaf $featureJson.feature_directory
$iterationsRoot = Join-Path $featureJson.feature_directory 'iterations'
$iterationNumber = if (Test-Path -LiteralPath $iterationsRoot -PathType Container) {
    @(Get-ChildItem -LiteralPath $iterationsRoot -Directory | Sort-Object Name -Descending | Select-Object -First 1)[0].Name
}
pwsh -File .\.specify\extensions\specrew-speckit\scripts\sync-boundary-state.ps1 -ProjectPath . -BoundaryType retro -FeatureRef $featureRef -IterationNumber $iterationNumber

If the sync fails, stop and report the exact file-write error before continuing. If the sync is refused because an earlier crossing is still unapproved (the ratchet), that refusal IS the stop — surface it and wait for the human; do not work around it.

Advancement gate (after the arrival is recorded)

The gate BLOCKS until the human's verdict authorizes this crossing:

. .\.specify\extensions\specrew-speckit\scripts\shared-governance.ps1
$authorization = Test-SpecrewBoundaryAuthorization -ProjectRoot . -CurrentBoundary 'review-signoff' -RequestedBoundary 'retro'
if (-not $authorization.Authorized) {
  Write-Output (Write-SpecrewBoundaryAuthorizationDirective -CurrentBoundary $authorization.CurrentBoundary -RequestedBoundary $authorization.RequestedBoundary -DirectiveSentinel $authorization.DirectiveSentinel)
  throw $authorization.Reason
}

On a gate block, .specrew/runtime/pending-verdict-stop.md is the controller truth: render the six-section boundary packet from its Boundary to ask for, Human approval phrase, and Marker last line exactly values, then stop for the human's verdict. Do not infer a marker from the phase you are in.

Read the full file on GitHub · 47 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. 5d ago First seen · 47 lines · 10 tokens per session scan A d94e14186bf3

Subscribe to this mod's changes

speckit.specrew-speckit.sync-retro is a command published in the GitHub repository alonf/specrew (54 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 592 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to speckit.specrew-speckit.sync-clarify, differing in 22 lines, and is treated as a copy.