Borrowing it
Nothing to install: this file belongs to andreaswasita/copilot-agents-dojo. 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/andreaswasita/copilot-agents-dojo/main/.github/prompts/dojo-swarm.prompt.mdgit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/commands/andreaswasita/copilot-agents-dojo/dojo-swarm)<a href="https://agentmods.dev/commands/andreaswasita/copilot-agents-dojo/dojo-swarm"><img src="https://agentmods.dev/badge/commands/andreaswasita/copilot-agents-dojo/dojo-swarm/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/commands/andreaswasita/copilot-agents-dojo/dojo-swarm"><img src="https://agentmods.dev/badge/commands/andreaswasita/copilot-agents-dojo/dojo-swarm.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 | $0.00012 | $0.00563 |
| Opus 5.5 | $0.00005 | $0.00225 |
| Sonnet 5.5 | $0.00002 | $0.00113 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
dojo-swarm 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.
What it actually says
Run the dojo swarm — the parallel variant of the mandatory workflow — for the goal I give you.
Scaffold with bash scripts/sprint.sh start "<goal>" --swarm, then walk the same phases:
- BRAINSTORM — read
skills/brainstorming/SKILL.md: Socratic refinement into an approved design - WORKTREE — read
skills/using-git-worktrees/SKILL.md: Isolated workspace on a feature branch - PLAN — read
skills/plan-before-code/SKILL.md: Bite-sized tasks written to tasks/todo.md - EXECUTE — read
skills/executing-plans/SKILL.md: One task at a time, verifying each before the next - TEST — read
skills/test-writing/SKILL.md: RED then GREEN then REFACTOR for every behaviour change - REVIEW — read
skills/requesting-code-review/SKILL.md: Self-review the diff against the plan - FINISH — read
skills/finishing-a-development-branch/SKILL.md: Verify, decide the merge, clean up the branch - LEARN — read
skills/self-improvement/SKILL.md: Log lessons, promote patterns, update the memory vault
Coordination rules for the parallel section (read skills/dispatching-parallel-agents/SKILL.md):
- Keep BRAINSTORM, WORKTREE, and PLAN sequential — design and task-splitting happen once, up front.
- Split EXECUTE + TEST into independent board tasks, one per sub-agent; no two sub-agents touch the same files.
- Respect the subagent depth/concurrency limits in AGENTS.md.
- Fan in at REVIEW: collect the sub-agents' diffs and self-review the combined change against the plan.
- Run a single central
bash scripts/sprint.sh finish— the gate and merge decision happen once, not per sub-agent.
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 · 27 lines · 12 tokens per session scan A c82834116b0c
dojo-swarm is a command published in the GitHub repository andreaswasita/copilot-agents-dojo (54 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 563 once invoked, about $0.0000 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 2026-09-07.
Other commands, from other repositories
meta-theory-verify
Run the appropriate MetaKim verification path.
dev-tdd
Implements a feature by following the TDD (Test-Driven Development) cycle.
ops-load-testing
Command "ops-load-testing" from christopherlouet/claude-base, covering ops-load-testing agent, request context, objective, workflow and expected output.
qa-tech-debt
Identification and prioritization of technical debt in the codebase.
work-flow-bugfix
Complete workflow to fix a bug, from diagnosis to deployment.
dev-debug
Methodical and systematic bug diagnostic and resolution.