Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. 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/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/commands/setup-project.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/everyone-needs-a-copilot/claude-copilot/setup-project)<a href="https://agentmods.dev/commands/everyone-needs-a-copilot/claude-copilot/setup-project"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/setup-project/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/everyone-needs-a-copilot/claude-copilot/setup-project"><img src="https://agentmods.dev/badge/commands/everyone-needs-a-copilot/claude-copilot/setup-project.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 | $0.00000 | $0.01260 |
| Opus 5.5 | $0.00000 | $0.00504 |
| Sonnet 5.5 | $0.00000 | $0.00252 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade B, and why
setup-project scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$REQUEST_FILE" How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Project
Install the complete Claude + Codex reference through the canonical cc transaction. Never manually copy framework files. The transaction installs executable .claude/hooks/copilot-hook.sh, registers supported hook events and records the shim in copilot.lock.json. Verification rejects a missing, non-executable, unregistered or unlocked shim.
The former partial minimal / quick start profile is retired. If requested, explain complete setup preserves memory and project-authored files and ask whether to continue; a decline stops without mutation. Repair existing minimal installs through this transaction.
Solo and organization setups
Without configured or inherited organization settings, solo setup needs no sign-in, layer manifest or signed pins. Layers report not-configured; personal/local content and full hook wiring still install. When an organization is configured, all organization checks apply: broken or signed-out configurations block.
Projects must be inside projects.roots. If outside, ask the person to confirm a folder, run cc config add projects.roots "<absolute folder>" and retry. Prefer the project or parent folder, never $HOME.
0. Verify the local CLI prerequisites
Both Copilot CLIs must be ready. The cc-owned prerequisite fact rejects macOS' unrelated C compiler and names machine setup as recovery. Never plan or mutate on failed prerequisites.
1. Build and inspect the exact plan
Run from the project root. Planning is read-only; shell exit removes the temporary request.
set -eu
CC_BIN=""
for CANDIDATE in "$(command -v cc 2>/dev/null || true)" "$HOME/.local/bin/cc"; do
if [ -n "$CANDIDATE" ] && [ -x "$CANDIDATE" ] && "$CANDIDATE" --version 2>/dev/null | grep -q '^cc version'; then
CC_BIN="$CANDIDATE"
break
fi
done
if [ -z "$CC_BIN" ] || ! command -v tc >/dev/null 2>&1; then
echo "Claude Copilot machine setup is required: the Copilot cc and tc CLIs must both be available. Open ~/.claude/copilot, run /setup, open a fresh shell, then retry." >&2
exit 3
fi
PROJECT_ROOT="$(git rev-parse --show-toplevel)"
REQUEST_FILE="$(mktemp -t cc-project-request.XXXXXX)"
trap 'rm -f "$REQUEST_FILE"' EXIT
chmod 600 "$REQUEST_FILE"
"$CC_BIN" reconcile request --project "$PROJECT_ROOT" --output "$REQUEST_FILE"
"$CC_BIN" reconcile plan --request "$REQUEST_FILE" --json
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 Changed · -29 lines 4e4b7f1625f1
- 7d ago Changed · +18 lines b86c5f63800b
- 15d ago Changed · -34 lines 683b125f291d
- 1mo ago First seen · 130 lines · 0 tokens per session scan B 6f402a36511e
setup-project is a command published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,260 tokens. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.