What is sync-downstream-harness?

A command that copies updated command and workflow files from a base template into repositories created from it. It normally previews the changes and can apply them when requested.

Use it to review or apply shared harness updates to all eligible repositories, or to one selected repository.

It avoids repeating the same template updates manually across many repositories, without deleting each repository's custom files.

How bredmond1019/claude-sdk-rs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. 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/bredmond1019/claude-sdk-rs/main/.claude/commands/sync-downstream-harness.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

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/commands/bredmond1019/claude-sdk-rs/sync-downstream-harness/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/sync-downstream-harness)

Your own site

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/sync-downstream-harness"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sync-downstream-harness/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/commands/bredmond1019/claude-sdk-rs/sync-downstream-harness"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/sync-downstream-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,130 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00050	$0.02130
Opus 5.5	$0.00020	$0.00852
Sonnet 5.5	$0.00010	$0.00426
Haiku 4.5	$0.00005	$0.00213

Measured 11d ago against content hash fc57478e141f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

sync-downstream-harness scanned grade B with 1 finding 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 11d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cd <repo_path> && git status --short | grep -v '\.claude/' | grep -v 'planning/\.template-version'

.claude/commands/sync-downstream-harness.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sync-downstream-harness — Pull the harness into every scaffolded repo

Automates the manual "update loop" docs/using-the-template.md §6 describes: copies base-template's current .claude/commands/*.md (flat root only — never .claude/commands/brain/) and .claude/workflows/ (the SDLC engines + templates/) into every repo discovered via brain.toml that already has its own .claude/workflows/ directory. Never deletes a repo's own customizations (e.g. feature.md). See planning/decisions/D48-downstream-harness-sync-script.md for why this exists — .claude/workflows/*.js has no equivalent of /sync-global-commands' global install path, so a harness fix here doesn't reach a downstream repo until this runs.

Variables

$ARGUMENTS — optional flags, space-separated:

--repo <slug> — limit to one repo (repeatable: --repo bastion --repo mev). Default: all eligible repos.
--apply — write changes. Default is dry-run (report only, nothing written).
--message "<text>" — description recorded in each synced repo's planning/.template-version. Default: "harness pull". Use something specific (e.g. the decision id driving the pull).

Instructions

Guard — confirm you are in the base-template root.

Run:

test -f .claude/workflows/sdlc-flow.js && echo "Guard: OK — running from base-template root" || echo "ABORT: .claude/workflows/sdlc-flow.js not found. Run this command from the base-template root."

Dry run first, always — even if $ARGUMENTS includes --apply, run once without it first so the report is visible before anything is written:
```
python3 scripts/sync_downstream_harness.py <$ARGUMENTS minus --apply, if present>
```
Read the per-repo file list. If a repo shows an unexpectedly large diff (e.g. hundreds of lines in one engine file), that's very likely just a stale repo catching up several pulls at once — confirmed harmless in practice (D48's provenance) via diff <target file> <base-template file> showing the sync produces a byte-identical copy, not corruption. Flag it in the report either way.

Read the full file on GitHub · 139 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.

11d ago First seen · 139 lines · 50 tokens per session scan B fc57478e141f

Subscribe to this mod's changes

sync-downstream-harness is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 2,130 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.

D48 Git and workflow Project management Workflows downstream sync harness pull propagation template-version

sync-downstream-harness next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sync-downstream-harnessbredmond1019/claude-sdk-rs	Command	23	1mo ago	Apache-2.0	B	50	Claude Code
commitguanyang/open-agent-hub	Command	986	yesterday	MIT	A	28	Claude Code
commithowells/arc	Command	25	2mo ago	MIT	A	18	Claude Code
releasehowells/arc	Command	25	2mo ago	MIT	A	23	Claude Code
merge-conflict-analysisrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
release-notesOpenHands/extensions	Command	176	yesterday	MIT	A	44	Claude Code
commitechoVic/blade-code	Command	181	24d ago	MIT	A	8	Claude Code

claude-sdk-rs: Command for Claude Code