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.
git clone --depth 1 https://github.com/alonf/specrewWrote 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.
[](https://agentmods.dev/commands/alonf/specrew/speckit.specrew-speckit.sync-retro)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
- 5d ago First seen · 47 lines · 10 tokens per session scan A d94e14186bf3
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.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.