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 commands/santiquiroz/copilot-plugin-cc/setupgit clone --depth 1 https://github.com/santiquiroz/copilot-plugin-ccWhat 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 | $0.00016 | $0.00463 |
| Opus 5 | $0.00008 | $0.00231 |
| Sonnet 5 | $0.00003 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
setup 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 yesterday.
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 these checks in order and report a single consolidated status at the end.
Step 1 — Installed?
Run:
copilot --version
- If the command is not found and
npmis available: useAskUserQuestionexactly once with two options —Install GitHub Copilot CLI (Recommended)andSkip for now. If the user chooses install, runnpm install -g @github/copilot, then reruncopilot --version. - If the command is not found and
npmis unavailable: report the official install docs (https://docs.github.com/en/copilot/how-tos/set-up/install-copilot-cli) and stop.
Step 2 — Version gate
- If the reported version is lower than 1.0.67: warn that multi-model selection (
--model) is unsupported on this version and recommendnpm update -g @github/copilot. Continue with the remaining checks.
Step 3 — Authentication probe
Run:
copilot -p "Reply with exactly one word: ready" -s --deny-tool=shell --deny-tool=write
- Output contains
ready→ authenticated and working. - Output shows an authentication error → instruct the user to either run
copilotinteractively and use/login, or set theCOPILOT_GITHUB_TOKENenvironment variable with a token that has Copilot access. NEVER print or echo the token value. - Output contains "rate limit" (case-insensitive) → report that the Copilot quota is currently exhausted; delegation is unavailable until it resets.
Step 4 — Consolidated report
Summarize in one short block: install state, version (and whether it meets the 1.0.67 floor), auth state, and model options — pin with --model <name> or the COPILOT_MODEL environment variable for deterministic behavior; omit (or use --model auto) to allow Auto-selection, which carries a billing discount on routine mechanical work.
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.
- yesterday First seen · 39 lines · 16 tokens per session scan A 7bd7e74bfc12
setup is a command published in the GitHub repository santiquiroz/copilot-plugin-cc (1 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 463 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 2026-08-31.
Other commands, from other repositories
speckit.assess.decide
Command "speckit.assess.decide" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the decide stage.
speckit.assess.define
Command "speckit.assess.define" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the define stage.
speckit.assess.intake
Command "speckit.assess.intake" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the intake stage.
speckit.assess.research
Command "speckit.assess.research" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the research stage.
speckit.assess.shape
Command "speckit.assess.shape" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the shape stage.
speckit.analyze
When executing this command, delegate independent work to parallel sub-agents to reduce total execution time.