github-sync

A deprecated command for syncing SpecWeave increments with GitHub Issues, GitHub’s collaborative work-tracking pages. The newer spec-based sync works at the user-story level.

In plain words
What is it for?
Use the replacement spec-sync command for syncing one specification or all specifications, including optionally importing changes from GitHub.
Why use it?
It warns you that this older increment-based workflow can produce issues at the wrong level and may show outdated content if documents were not synced first.

Command

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/anton-abyzov/specweave/github-sync
Clone the repo
git clone --depth 1 https://github.com/anton-abyzov/specweave
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,909 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 $0.00020 $0.04909
Opus 5 $0.00010 $0.02455
Sonnet 5 $0.00004 $0.00982
Haiku 4.5 $0.00002 $0.00491

Measured 2d ago against content hash 035c99d0f1fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-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 2d 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.

plugins/specweave/commands/github-sync.md · 702 lines

How it starts

The opening of the file, as written. The whole thing — 702 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEPRECATED: Use sw-github:sync-spec Instead

This command is deprecated as of v1.0.235. The increment-based sync has been replaced by spec-based sync.

Migration:

  • For spec-to-GitHub Issue sync: sw-github:sync-spec <spec-id>
  • For batch sync: sw-github:sync-spec --all
  • For pull direction: sw-github:sync-spec <spec-id> --direction from-github

The old increment-based sync created issues per-task. The new spec-based sync creates issues per-User-Story, which is the correct granularity for GitHub project management.


Legacy: Sync Increment with GitHub Issue (Multi-Project)

Pre-Sync Requirements (Read First!)

⛔ MANDATORY: Sync Living Docs BEFORE GitHub Sync

GitHub sync reads FROM living docs. If living docs are stale, GitHub issues will have outdated content.

You MUST run sw:sync-specs (or ensure it ran) BEFORE this command:

# STEP 1: Ensure living docs are current (MANDATORY)
sw:sync-specs <increment-id>

# STEP 2: Then sync to GitHub
sw-github:sync <increment-id>

Why?

  • GitHub issues are generated FROM .specweave/docs/internal/specs/FS-XXX/
  • If you skip sync-specs, GitHub will show stale user stories/ACs
  • sw:sync-progress calls sync-specs automatically, but sw-github:sync does NOT

If you're calling this directly (not via sw:sync-progress), run sync-specs first!


Step 0: Detect Project Structure

# Check for living docs structure
if [ -d ".specweave/docs/internal/specs" ] && [ -n "$(ls -A .specweave/docs/internal/specs/*/FEATURE.md 2>/dev/null)" ]; then
    echo "✅ Living docs found → Use Feature Sync"
else
    echo "⚠️ No living docs → Use Increment Sync (brownfield)"
fi

Sync Path Decision:

Structure Command Issue Format
Living docs exist (.specweave/docs/internal/specs/FS-XXX/) Use github-feature-sync-cli.ts [FS-XXX][US-YYY] Title
Increment only (brownfield, no living docs) Use github-feature-sync-cli.ts [FS-XXX] Title with ACs

Read the full file on GitHub · 702 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. 2d ago First seen · 702 lines · 20 tokens per session scan A 035c99d0f1fa

Subscribe to this mod's changes

github-sync is a command published in the GitHub repository anton-abyzov/specweave (159 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 4,909 once invoked, about $0.0001 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 2026-08-30.