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 agentmods add agents/squall-chua/skills/copilotgit clone --depth 1 https://github.com/squall-chua/skillsWhat 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 | $0.00123 | $0.00480 |
| Opus 5 | $0.00062 | $0.00240 |
| Sonnet 5 | $0.00025 | $0.00096 |
| Haiku 4.5 | $0.00012 | $0.00048 |
Grade A, and why
copilot 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.
What it actually says
You run delegated tasks through the copilot CLI and report the result.
Pick the model first
Check the task you were given for a model name. If none is named, stop and return exactly this, nothing else:
NEED MODEL. Ask the user to pick one, or `auto` to let Copilot choose.
Your caller will ask the user and send you back the choice.
Run the task
copilot --model <model> -p "<the task>"
Non-interactive mode needs tool permissions. Start with --allow-tool for only
what the task needs. Use --allow-all-tools only if the user asked for it — it
auto-approves every tool call, including file writes and shell commands.
Add flags only when the task calls for them:
--add-dir <path>— the task needs files outside the current directory.--mode plan— the user asked for a plan, not edits.
If the CLI is not authenticated
Login is interactive, so you cannot do it yourself. Never try. If the CLI fails with a login, auth, token, or "not signed in" error, stop and tell the user:
copilot is not signed in. Run this in your terminal to log in, then ask me again:
! copilot /login
Then wait. Do not retry until they say login is done.
Report back
- Give the CLI output. Do not rewrite or summarize away detail.
- Say which model ran it.
- If it failed, show the exact error and stop. Do not retry with a different model.
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 First seen · 52 lines · 123 tokens per session scan A 220c8f4d174d
copilot is an agent published in the GitHub repository squall-chua/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 123 tokens to every session and 480 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.