agentleFS
metagit-aimetagit-ai/metagit-cli/skills/metagit-campaign/SKILL.md

metagit-campaign

Skill4 starsChanged 13 days agoMITView on GitHub

Plan and track cross-project multi-repo campaigns — YAML overlays, repo rollups, objective fan-out, and MR status. Use for umbrella-scale coordinated work.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when coordinating many repos under one intent (rollout, migration, tier stamp) with a committed, diffable status overlay.

    line 13
  2. Distinctive:

    When operating on a campaign:

    line 76
  3. Very specific:

    Check whether an EverRoom provider is attached (campaign everroom status).

    line 80
  4. Distinctive:

    Use MetaGit for topology, Git state, and relationships.

    line 82
  5. Distinctive:

    Use EverRoom for rationale, evidence, decisions, and historical context.

    line 83
  6. Distinctive:

    Do not treat generated summaries as authoritative over source material.

    line 84
  7. Distinctive:

    Do not retrieve unrelated Room/global context through MetaGit.

    line 86
  8. Very specific:

    If EverRoom is down, campaign context still returns MetaGit-only data with a warning.

    line 98
  9. Very specific:

    Never store tokens in _campaigns/*.yml.

    line 100

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Metagit campaign skill

<!-- modality:native_campaigns --><!-- modality:campaign_everroom_context --><!-- modality:campaign_board_link --><!-- modality:objective_mr_approval_binding --><!-- modality:coordination_events_scope -->

Use when coordinating many repos under one intent (rollout, migration, tier stamp) with a committed, diffable status overlay.

Docs: campaigns.md · campaign-everroom.md · Registry: modality-feature-registry.md

When to use

  • One selection query → frozen repo list → per-repo status/MR tracking
  • Fan-out spine objectives for parallel agents (campaign expand)
  • Rollup: merged vs open MR vs blocked without manual spreadsheets
  • Combined Campaign Context from MetaGit topology plus optional EverRoom evidence

Configuration

# metagit.config.yaml
workspace:
  campaigns_path: _campaigns   # default; or knowledge/campaigns

Env: METAGIT_WORKSPACE_CAMPAIGNS_PATH

Lifecycle

export METAGIT_AGENT_MODE=true

metagit campaign new --slug tier-full --title "Full-tier rollout" \
  --query "platform" --tag agent_tier=full
metagit campaign validate
metagit campaign expand --slug tier-full --dry-run
metagit campaign expand --slug tier-full
metagit campaign set --slug tier-full --repo platform/api --status merged --mr "https://…"
metagit campaign status --slug tier-full --json --limit 40

--json on new/status/set/expand returns counts + a page, not the overlay YAML. Page with --offset. Freeze up to 2000 matches on disk; never paste _campaigns/*.yml into the conversation.

Board linking (Azure DevOps)

<!-- modality:campaign_board_link -->

Pointer on the campaign or a repo row (provider, id, url, organization, project, kind). Tokens stay in AppConfig / METAGIT_AZURE_DEVOPS_*.

metagit campaign new --slug payments --title "Payments" --query payments \
  --work-item azure_devops:12345 --json
metagit campaign board-sync --slug payments --organization myorg --ado-project platform \
  --dry-run --json
metagit campaign board-sync --slug payments --organization myorg --ado-project platform \
  --limit 40 --offset 0 --json

MCP: metagit_campaign_status, metagit_campaign_board_sync (dry_run: true first). Docs: context-reduction.md.

Campaign Context (optional EverRoom)

<!-- modality:campaign_everroom_context -->

A campaign is the technical/work boundary. An EverRoom Room is the context/evidence boundary.

  • MetaGit answers: "What exists and what is affected?"
  • EverRoom answers: "What do we know, why did we decide it, and what context surrounds it?"

When operating on a campaign:

  1. Identify the campaign slug.
  2. Inspect MetaGit technical scope (campaign status / campaign context).
  3. Check whether an EverRoom provider is attached (campaign everroom status).
  4. Retrieve Campaign Context (campaign context --json or MCP metagit_campaign_context).
  5. Use MetaGit for topology, Git state, and relationships.
  6. Use EverRoom for rationale, evidence, decisions, and historical context.
  7. Do not treat generated summaries as authoritative over source material.
  8. Cite source=metagit vs source=everroom.
  9. Do not retrieve unrelated Room/global context through MetaGit.
export METAGIT_EVERROOM_URL=http://127.0.0.1:3210
export METAGIT_EVERROOM_TOKEN=…    # never put this in YAML, Git, or prompts

metagit campaign everroom attach --slug terraform-hcp-migration --room room_01J…
metagit campaign context --slug terraform-hcp-migration --json
metagit campaign everroom sync --slug terraform-hcp-migration
metagit campaign everroom detach --slug terraform-hcp-migration

If EverRoom is down, campaign context still returns MetaGit-only data with a warning. attach/sync fail instead of mutating blindly.

Never store tokens in _campaigns/*.yml. Room id ≠ campaign slug.

Agent posture before repo work

metagit agent profile show -p platform -n api --json
metagit agent apply --vendor claude_code --project platform --repo api

Orchestrator polling

metagit context events --campaign tier-full --since "<iso-cursor>" --json

Related skills

  • metagit-multi-repo · metagit-control-center · metagit-context-pack

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.