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/acaprino/daodan/team-codebase-mapgit clone --depth 1 https://github.com/acaprino/daodanWhat 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 | $0.00053 | $0.02783 |
| Opus 5 | $0.00026 | $0.01392 |
| Sonnet 5 | $0.00011 | $0.00557 |
| Haiku 4.5 | $0.00005 | $0.00278 |
Grade B, and why
team-codebase-map 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
The team infrastructure itself (teammate spawning via the `Agent` tool, plus TaskList) is a native Claude Code feature and needs no plugin, but it is experimental and OFF by default: it requires `CLAUDE_CODE_EXPERIMENTAL How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
This command requires the upstream agent-teams plugin from wshobson/agents (MIT, Seth Hobson). It provides the agent-teams:task-coordination-strategies and agent-teams:team-communication-protocols skills used below. Install it first:
/plugin marketplace add wshobson/agents
/plugin install agent-teams@claude-code-workflows
The team infrastructure itself (teammate spawning via the Agent tool, plus TaskList) is a native Claude Code feature and needs no plugin, but it is experimental and OFF by default: it requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1, best set persistently in the env block of ~/.claude/settings.json. As of Claude Code 2.1.178 there are no TeamCreate/TeamDelete tools: the team forms implicitly when the first teammate is spawned, and team resources are cleaned up automatically when the session ends. If teammate spawning is unavailable in this session, stop and tell the user to enable the flag and restart Claude Code; do not fall back to plain subagents without saying so.
Team Codebase Map
Orchestrate the codebase-mapper pipeline using parallel agent teams. Phase 2 runs 6 writers simultaneously, dramatically reducing total documentation time.
Skills to Load
Before starting, invoke these skills:
codebase-mapper:codebase-mapper-- writing guidelines, tone rules, diagram conventionsagent-teams:task-coordination-strategies-- phased task dependenciesagent-teams:team-communication-protocols-- coordination between writers
Pre-flight Checks
- Verify
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1is set - Parse
$ARGUMENTS:[target-path]: project root to map (default: current working directory)--skip-review: skip Phase 3 reviewer pass--writers N: limit parallel writers (default: 6, min: 1, max: 6)
Pipeline Overview
The sequential map-codebase command runs agents one-by-one. This team version parallelizes Phase 2:
Phase 1: Explore (sequential -- 1 agent)
- codebase-explorer builds context brief
|
v
Phase 1b: Interconnect Map (sequential -- 1 agent)
- semantic-interconnect-mapper builds structured facts
(contracts, invariants, domain rules, integration hot-spots)
|
v
Phase 2: Write (parallel -- 6 agents)
- overview-writer --> 01-overview.md, 02-features.md
- tech-writer --> 03-tech-stack.md, 04-architecture.md [reads interconnect]
- flow-writer --> 05-workflows.md, 06-data-model.md [reads interconnect]
- onboarding-writer --> 07-getting-started.md, 08-open-questions.md
- ops-writer --> 09-project-anatomy.md [reads interconnect]
- config-writer --> 10-configuration-guide.md
|
v
Phase 3: Review (sequential -- 1 agent)
- guide-reviewer --> INDEX.md [drift detection]
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 · 190 lines · 53 tokens per session scan B fb8d7b6cdb71
team-codebase-map is a command published in the GitHub repository acaprino/daodan (8 stars, last pushed 7d ago), licensed MIT. It adds 53 tokens to every session and 2,783 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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.