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.
npx skills add metagit-ai/metagit-cli --skill metagit-sharing-stategit clone --depth 1 https://github.com/metagit-ai/metagit-cliWrote 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/skills/metagit-ai/metagit-cli/metagit-sharing-state)<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-sharing-state"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-sharing-state/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.
<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-sharing-state"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-sharing-state.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.01389 |
| Opus 5.5 | $0.00029 | $0.00556 |
| Sonnet 5.5 | $0.00015 | $0.00278 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
metagit-sharing-state 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metagit shared coordination state
Use when more than one agent or machine must read/write the same objectives,
handoffs, approvals, and event feed — without syncing .metagit/sessions/*.json
via Syncthing.
Full references:
- docs/reference/sharing-state.md — HTTP ops contract
- docs/reference/central-state-plane.md — plane backends, extras, org/workspace ids, Dynamo bootstrap
When to use
- Hermes controller + subagents on different hosts
- Human on Metagit Web + agents on MCP/CLI
- CI runner updating objectives while developers use Cursor MCP
- Org-scale coordination on DynamoDB / MongoDB (RFC-0015)
Prefer shared state (HTTP or cloud DocumentStore) over Syncthing for
coordination JSON when agents run on separate machines. Keep Syncthing (or git)
for .metagit.yml catalog edits only.
Backends
| Backend | Extra | Typical use |
|---|---|---|
local |
— | Single machine default |
http |
— | Agents → metagit web serve via METAGIT_STATE_URL |
memory |
— | Tests only |
dynamodb |
metagit-cli[state-dynamodb] |
Direct cloud or ops-server-hosted |
mongodb |
metagit-cli[state-mongodb] |
Direct cloud or ops-server-hosted |
uv tool install 'metagit-cli[state-dynamodb]'
uv tool install 'metagit-cli[state-mongodb]'
Coordinator setup (HTTP / deployment B)
On one host with the workspace manifest (local JSON or cloud DocumentStore on the server):
metagit web serve --host 127.0.0.1 --port 8787
# production: TLS reverse proxy + bearer token in front
# optional: METAGIT_STATE_BACKEND=dynamodb + table/region on this host only
Agents keep METAGIT_STATE_URL — they do not need cloud extras when the
coordinator hosts Dynamo/Mongo.
Client setup (CLI, MCP, every agent host)
App config (~/.config/metagit/config.yml):
config:
state:
backend: http
url: https://coordinator.example.com:8787
token: your-bearer-token
conflict_retries: 1
org_id: "" # optional plane partition
workspace_id: ""
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.
- 1mo ago First seen · 154 lines · 73 tokens per session scan A 18a6bd9b8f96
metagit-sharing-state is a skill published in the GitHub repository metagit-ai/metagit-cli (4 stars, last pushed 24d ago), licensed MIT. It adds 73 tokens to every session and 1,389 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
repository-manager-fleet-scale-operations
Run development across MANY repositories and many concurrent lanes at once — bulk worktree creation, workspace-wide worktree audits and classification (merged / active / stale / dangling / orphaned), safe mass pruning, draining several repositories' merge queues in parallel, and sizing concurrency against the real…
repository-manager-workspace-release
Preview the topologically-phased version-bump plan across a workspace, drive validation with an explicitly consented chain into version bump and phased push, and manage the workspace.yml manifest — via rmworkspace and rmprojects. Nothing here pushes or bumps without an explicit opt-in on the call that triggers it…
daf-workflow
DevAIFlow session context loader — reads session metadata, issue tracker tickets, and context files. Auto-activates when DAFSESSIONNAME is set. Also useful when asked about current task, session status, or workflow steps for daf open, daf new, daf git new, daf jira new, and daf investigate.
project-ops
Use when an operator wants to run a small or mid-sized project from a flat file instead of standing up Jira or Asana — dated milestones each with one named owner and a binary done-test, rule-driven RAG status, a RAID log, slippage detection, and a two-minute weekly status report. NOT sequencing the engineering work…
meegle
A guide and command-line interface for managing Feishu/Lark Meego project data, including work items, workflow steps, views, personal tasks, and schedules. Feishu/Lark is a collaboration platform, while Meego is its project-management system.