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/gosha70/code-copilot-team/list-agentsgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWhat 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 | $0.00000 | $0.00410 |
| Opus 5 | $0.00000 | $0.00205 |
| Sonnet 5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
list-agents 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
List the custom subagents installed on this machine and in this project — the replacement for the built-in /agents command removed from recent Claude Code versions.
Note: built-in agent types (e.g. general-purpose, Explore) and plugin-supplied agents have no file in these directories and are not covered by this roster.
Usage: /list-agents [name]
Steps
1. Collect agent definitions
Scan both scopes:
- Global:
~/.claude/agents/*.md - Project:
.claude/agents/*.md(relative to the project root)
Read each file's YAML frontmatter: name, description, tools, model. If name is missing, use the filename without .md.
2. Detail view (with argument)
If [name] is given, show only that agent in full: scope, file path, description, model, tools, and a short excerpt (first ~20 lines) of its system prompt body. If nothing matches, say so and list the available names.
3. Roster view (no argument)
Print one table per scope, project scope first:
| Agent | Model | Tools | Description |
|---|
- A project-level agent overrides a global agent with the same name — mark the shadowed global entry as
(shadowed). - If a scope's directory is missing or empty, say so on one line; do not treat it as an error.
- If no agents are found in either scope, explain that this machine has no agent setup installed and point to
adapters/claude-code/setup.sh(fresh install) orsetup.sh --sync(update) in the code-copilot-team repo, which installs the standard team (research, plan, build, review, and the utility agents).
4. Read-only
Do not create, edit, or delete any agent files. This command only reports.
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 · 36 lines · 0 tokens per session scan A f77010fb60be
list-agents is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 tokens. 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.