harness-sync

harness-sync is a skill for Claude Code from larsboes/Axon. It costs 182 tokens per session (1,419 once invoked), scanned A, original, MIT.

A tool and decision guide for keeping copies of AI-agent skills consistent across Axon and installed agent environments. It distinguishes routine copying from deliberately bringing an edited copy back into the source.

In plain words
What is it for?
Listing installed agent environments, checking for drift, syncing source changes, and accepting or promoting edits made in a deployed copy.
Why use it?
It prevents accidental overwrites or importing unwanted edits by making the direction of each change explicit. It also identifies drift between the source and deployed copies.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Part of the harness plugin — 3 skills shipped together

Good fit Listing installed agent environments, checking for drift, syncing source changes, and accepting or promoting edits made in a deployed copy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/larsboes/axon/harness-sync
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.

Any agent
npx skills add larsboes/Axon --skill harness-sync
Clone the repo
git clone --depth 1 https://github.com/larsboes/Axon

Made for: Claude Code.

Or install harness, the plugin that ships this one along with the rest of its 3 skills.

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 harness-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/larsboes/axon/harness-sync/github.svg)](https://agentmods.dev/skills/larsboes/axon/harness-sync)
Your own site
<a href="https://agentmods.dev/skills/larsboes/axon/harness-sync"><img src="https://agentmods.dev/badge/skills/larsboes/axon/harness-sync/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.

agentmods 80×15 button for harness-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/larsboes/axon/harness-sync"><img src="https://agentmods.dev/badge/skills/larsboes/axon/harness-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,419 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00182 $0.01419
Opus 5 $0.00091 $0.00709
Sonnet 5 $0.00036 $0.00284
Haiku 4.5 $0.00018 $0.00142

Measured 7d ago against content hash 9379ba001c7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, from the pricing page.

Security

Grade A, and why

harness-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 7d 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.

Packs/harness/skills/harness-sync/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

harness-sync

Axon is the source. Every harness holds a copy or a pointer, and the two drift.

One tool answers all of it: tools/harnesses in the Axon repository. This skill is the judgment around it — which direction a change should travel, and when the answer is not sync.

The direction rule

Axon Packs  ──(sync, routine, one-way, overwrites)──▶  harness
Axon Packs  ◀──(promote / accept, manual, human decides)──  harness

Sync is the normal move and it is destructive at the destination by design. The reverse moves are manual because an edit made inside a harness is a decision, and a tool that guessed would either lose good work or import junk into the source of truth.

Situation Move
The Pack changed; the harness is behind sync
A deployed copy was edited in place and the edit is worth keeping accept
A deployed copy was edited in place and the edit is not worth keeping sync (discards it)
A skill exists in a harness, no Pack owns it, and it should be shared promote
A skill exists in a harness and belongs to that harness alone leave it; it shows as unowned every run, which is the honest state

Procedure

- [ ] 1. Ask which harnesses are installed
- [ ] 2. Read the matrix
- [ ] 3. Resolve drift before deploying anything
- [ ] 4. Move in one direction at a time
- [ ] 5. Re-read the matrix

1 — Installed, not merely supported. tools/harnesses list. A harness with an adapter is not a harness on this machine, and deploying to an absent one leaves skills in a directory nothing reads. Every verb defaults to installed harnesses only; --all-harnesses overrides it and needs a reason.

2 — Read the matrix. tools/harnesses status [<pack>]. One row per Pack skill, one column per harness: · current, o outdated, D drifted, M missing, blank not deployed. Under it, each harness lists what sits at its destination that no Pack owns:

Kind What it means What to do
copy An ordinary directory nobody claims A promote candidate. Read it first.
external Carries .git, .graphify_version or similar Never promote. Another installer owns it and re-syncs from its own remote; a copy in Axon is a fork that will silently pin it. Record it in upstreams.toml instead.
symlink Points into a product install Never promote. The target is the install; an upgrade updates it.

Read the full file on GitHub · 97 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. 7d ago First seen · 97 lines · 182 tokens per session scan A 9379ba001c7c

Subscribe to this mod's changes

harness-sync is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 182 tokens to every session and 1,419 once invoked, about $0.0009 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 2026-09-08.