Borrowing it
Nothing to install: this file belongs to ra3orblade/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ra3orblade/swarm/main/.claude/skills/plan/SKILL.mdgit clone --depth 1 https://github.com/ra3orblade/swarmWrote 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/ra3orblade/swarm/plan)<a href="https://agentmods.dev/skills/ra3orblade/swarm/plan"><img src="https://agentmods.dev/badge/skills/ra3orblade/swarm/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/ra3orblade/swarm/plan"><img src="https://agentmods.dev/badge/skills/ra3orblade/swarm/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 | $0.00055 | $0.00340 |
| Opus 5.5 | $0.00022 | $0.00136 |
| Sonnet 5.5 | $0.00011 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
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 2mo 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.
What it actually says
Plan
Produce a scannable snapshot of the Swarm roadmap. Read-only — never edit plan files while running this.
Sources (read in order)
docs/06-roadmap.md— the authoritative milestone tables (ID · Task · Status).git log --oneline -12— if afeat:/fix:commit is newer than a task's status note, flag that the plan may be one step behind.gh pr list --state open(ifghis available) — surface open PRs not yet reflected in the plan.
Output
- A short header line: current phase + one sentence on where things stand.
- One markdown table per milestone that has any ⚪/🟡 work left, columns:
ID | Task | Status. Use ✅ / 🟡 / ⚪ verbatim from the roadmap; keep task text short (trim the long status notes to a phrase). - Collapse fully-done milestones to a single line (e.g.
**M0 See everything** — ✅ done). - End with a Next section: the 1–3 most valuable unstarted tasks and why, matching the recommendations in the roadmap's dependency order.
Keep it tight — this is a status glance, not a full doc dump.
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.
- 2mo ago First seen · 22 lines · 55 tokens per session scan A 5b758594c131
plan is a skill published in the GitHub repository ra3orblade/swarm (14 stars, last pushed 3d ago), licensed Apache-2.0. It adds 55 tokens to every session and 340 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 2026-08-31.
Other skills, from other repositories
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
issue-creator
A guide for turning unclear user feedback from text, chat excerpts, or screenshots into a focused GitHub issue, a tracked software-work item. It preserves the original request and separates evidence from information that is still unknown.
swarm-plan
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
parallel-work-check
Apply before starting work on an existing branch. Checks for parallel work by other agents or developers that may supersede or conflict with your planned changes. Prevents wasted effort on stale branches.
status
Surfaces the current state of work in gflow-cli. Three variants at different levels of detail: full state (status), next task only (next), active plan identity (active). All variants run scripts/dev/activeplan.py and filter its output to the requested detail level.