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 andreaswasita/copilot-agents-dojo --skill subagent-strategygit 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/skills/andreaswasita/copilot-agents-dojo/subagent-strategy)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/subagent-strategy"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/subagent-strategy/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/andreaswasita/copilot-agents-dojo/subagent-strategy"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/subagent-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.01761 |
| Opus 5 | $0.00008 | $0.00881 |
| Sonnet 5 | $0.00003 | $0.00352 |
| Haiku 4.5 | $0.00002 | $0.00176 |
Grade A, and why
subagent-strategy 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Strategy Skill
Delegates focused work to Copilot sub-agents via the task tool so the parent context stays clean. Supports decomposition, where agents own different workstreams, and competition, where isolated agents attempt the same high-risk artifact before a judge and lead select the result. Does NOT apply when the work must outlive the current turn — use the durable board (skills/durable-work) for that, since sub-agents are cancelled if the parent is interrupted.
When to Use
- Research across docs, APIs, or unfamiliar code (research role).
- Log / stack-trace / performance-profile analysis (analysis role).
- Parallel investigation when the answer lives in multiple places.
- A one-way-door design or ambiguous artifact benefits from independent competing attempts.
- The main context is filling with exploratory output (>~20 file reads).
- Multiple independent questions to resolve.
- NOT for: reading one file, single
grep, work that must survive the turn.
Prerequisites
- Access to the
tasktool (Copilot built-in). - A clear, written mission for each sub-agent — vague delegation produces vague output.
- Awareness of the configured knobs in
.dojo/delegation.yaml(defaults:max_spawn_depth: 2,max_concurrent_children: 3,default_mode: background,sync_timeout_seconds: 180,max_mission_tokens: 1500).
How to Run
1. Choose decomposition or competition mode.
2. Define one mission, scope, deliverable, and success rubric.
3. Give every sub-agent an isolated, non-overlapping target.
4. Invoke the `task` tool with mode=background for independent work,
mode=sync only when you must block on the result.
5. Inspect evidence and artifacts; synthesize rather than forwarding summaries.
Quick Reference
| Role | Mission shape | Tool & mode |
|---|---|---|
| Research | "Find X across the codebase; report file:line citations." | task (background) |
| Analysis | "Diagnose this stack trace; report root cause and 3 candidate fixes." | task (background) |
| Refactor scout | "Identify code smells in path/; propose alternatives." |
task (background) |
| Test scout | "List untested branches in module/." |
task (background) |
| Self-review | "Audit my diff against tasks/todo.md; flag gaps." |
task (sync) |
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.
- 2d ago Changed · +40 lines 10ceda5eaa61
- 10d ago First seen · 105 lines · 16 tokens per session scan A 1e38207fdb80
subagent-strategy is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (53 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 1,761 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
parallel
Use when two or more pieces of work are genuinely independent — disjoint files, no shared state, no ordering edge — and should fan out across subagents, then be gathered and reconciled under a combined test suite. Decides WHAT can run concurrently; NOT the isolation it runs in (that is worktrees), NOT the per-unit TDD…
evolution-guide
Explains how Evolving Lite works when the user asks about the system, its features, or how to use it. Triggers on questions like "how does this work", "what is evolving lite", "what hooks are running", "explain the system".
agent-spawn
Use when you need to spawn a specialist sub-agent to handle a specific task domain without polluting the main session context.
decision-ledger
A session record for tracking unresolved decisions and drafting them into `.governance/claims/` when they are settled. It preserves both the decision and the reason behind it.
governance-bootstrap
A guided checklist for creating a project's governance system from scratch when no governance exists.
session-grounding
A session-start procedure for checking the current facts, scope, and work track in a governed project before taking action.