A workflow for synchronizing Story Driven Development documents between a local project and the SDD Flow server. It can pull drafts, enrich them with technical details, and publish updates.

Use it to check remote settings, pull drafts, add TODOs, acceptance criteria, and edge cases, then mark enriched change requests as ready for the next state.

It keeps local and remote change requests, bugs, and documentation aligned while making draft work more complete before publication.

How sifter-ai/sifter configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sifter-ai/sifter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sifter-ai/sifter/main/.agents/skills/sdd-remote/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/sifter-ai/sifter

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-remote/github.svg)](https://agentmods.dev/skills/sifter-ai/sifter/sdd-remote)

Your own site

<a href="https://agentmods.dev/skills/sifter-ai/sifter/sdd-remote"><img src="https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-remote/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sifter-ai/sifter/sdd-remote"><img src="https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-remote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 931 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 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.

Model	Per session	Once invoked
Fable 5.1	$0.00101	$0.00931
Opus 5.5	$0.00040	$0.00372
Sonnet 5.5	$0.00020	$0.00186
Haiku 4.5	$0.00010	$0.00093

Measured 2mo ago against content hash 5164c331ab5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sdd-remote 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 2mo 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.

.agents/skills/sdd-remote/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Remote — Pull, Enrich, Push

Purpose

Synchronize local SDD docs with remote updates (from the SDD Flow server), enrich draft content, and publish the enriched result to remote in active states.

This skill also applies when a remote worker job is dispatched from SDD Flow — the worker runs these same workflows on behalf of the user.

Detection

This workflow applies when:

.sdd/config.yaml exists in the project root with a remote: section configured
The user asks to update local state from remote, pull pending CRs/bugs/docs, enrich drafts, or push pending remote updates
A remote worker job prompt instructs you to follow this workflow

Before any pull/push operation, check remote configuration with sdd remote status.

Workflows

Enrich workflow — Change Request

Follow this sequence to enrich a draft CR:

Pull remote drafts:

sdd pull --crs-only

Generate the draft TODO list:

sdd drafts

Enrich the draft with technical details, acceptance criteria, edge cases, and any relevant information from the project documentation and comments.
Transition the enriched CR from draft to pending:

sdd mark-drafts-enriched

Push the enriched content:

sdd push

Enrich workflow — Document

Follow this sequence to enrich a document (e.g. a feature spec):

Pull remote drafts:

sdd pull --docs-only

Locate the document file in product/ or system/ and update its content with the enriched version.
Push the enriched content:

sdd push

If the document was in draft status, it transitions to new on the server.

Sync workflow — Project-level

Full project sync when the user asks for "the latest" or "pull everything and implement":

Pull the latest specs:

sdd pull

Run the sdd skill — it handles the full loop: open bugs, pending CRs, documentation sync, code implementation, mark-synced, and commit.
Push the local updates:

Read the full file on GitHub · 130 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.

2mo ago First seen · 130 lines · 101 tokens per session scan A 5164c331ab5f

Subscribe to this mod's changes

sdd-remote is a skill published in the GitHub repository sifter-ai/sifter (54 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 931 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.

Git and workflow Project management

sdd-remote next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sdd-remotesifter-ai/sifter	Skill	54	1mo ago	MIT	A	101	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	5d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code

sifter: Skill for Claude Code