Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install coreWrote 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/atretyak1985/swarmery/run-plan)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/run-plan"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/run-plan/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/atretyak1985/swarmery/run-plan"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/run-plan.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 | $0.00042 | $0.01023 |
| Opus 5.5 | $0.00017 | $0.00409 |
| Sonnet 5.5 | $0.00008 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
run-plan 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 today.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Turn a finished plan directory into shipped code with one command. The main session acts as controller: it parses the phase DAG, picks a route, dispatches executors with the plan's own prompts, reviews each result, and keeps durable progress. The plan is the spec; this skill is the runner.
Main session only. Subagents cannot spawn subagents, so this playbook can never be delegated.
Rules (never violate)
- Read the ledger first — phases marked reviewed-clean in
<task-dir>/logs/run-ledger.mdare DONE; never re-dispatch them. - Tick as you verify — flip each satisfied criterion
- [ ]→- [x]immediately, never in a batch; unsatisfied criteria stay unticked. - Write the
## Completion Reportinto the phase doc itself — the only per-phase summary the platform surfaces; areports/file is no substitute. Three fields are mandatory and written out even when empty: Blocked calls, Delegation cost, and the one-sentence What would have made this cheaper — omitting one is not the same as having nothing to report. Exact wording:workspace-plans/resources/plan-format.md. - Executors never commit — commits, pushes, MRs, migrations, and deploys are ASK-gated controller business.
- Never skip the re-review after a fix dispatch; review the reconciled tree, never the agent's own worktree.
- One worktree per concurrent implementer on route P — parallel edits to one checkout corrupt each other.
- Don't check in between phases — the ledger is the status, and a progress note belongs in the same message as the next dispatch. Stop and ask only when a phase cannot continue without the operator, or at one of rule 4's ASK-gated actions.
Resources
- Read
resources/execution-routes.mdat the start of a run: locating and parsing the plan, the pre-flight review, the route triage table and hand-off alternative, worktree isolation and reconciliation, and the S / P / W routes. - Read
resources/progress-contracts.mdbefore accepting a phase: ledger format, the progress and summary hard gates, invariants, landing a stack of PRs (bottom-up, sequence printed by${CLAUDE_PLUGIN_ROOT}/bin/land-stack.sh), and failure modes.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +2 lines 0290ae0db371
- 25d ago Changed · +4 lines 1bb667007fe7
- 1mo ago Changed · +1 lines 8a38a7a4e962
- 1mo ago Changed · +3 lines 210b40fa0ae5
- 1mo ago First seen · 87 lines · 42 tokens per session scan A 103396ef7b53
run-plan is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 42 tokens to every session and 1,023 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
execute
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification.
recipe-batch-invite-to-event
Add a list of attendees to an existing Google Calendar event and send notifications.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-create-shared-drive
Create a Google Shared Drive and add members with appropriate roles.
recipe-find-free-time
Query Google Calendar free/busy status for multiple users to find a meeting slot.
recipe-organize-drive-folder
Create a Google Drive folder structure and move files into the right locations.