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.
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboardingWrote 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/kumaran-is/claude-code-onboarding/update-codemaps)<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/update-codemaps"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/update-codemaps.svg" alt="Measured on agentmods" 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 | $0.01002 |
| Opus 5 | $0.00000 | $0.00501 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
update-codemaps 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/update-codemaps — Generate Token-Lean Architecture Snapshots
Generates and updates docs/CODEMAPS/ — compact, <1000-token snapshots of each service layer. Used to orient sub-agents and new sessions without loading entire codebases.
What It Generates
| File | Covers |
|---|---|
docs/CODEMAPS/spring-api.md |
Java 21 / Spring Boot 3.5.x WebFlux service |
docs/CODEMAPS/nestjs-api.md |
NestJS 11.x / Fastify / Prisma service |
docs/CODEMAPS/angular-spa.md |
Angular 21.x SPA |
docs/CODEMAPS/flutter-mobile.md |
Flutter 3.41.x mobile app |
docs/CODEMAPS/python-api.md |
Python 3.14 / FastAPI service |
docs/CODEMAPS/architecture.md |
Cross-service integration map |
Process
- Detect which services exist — check for
pom.xml,package.jsonwith NestJS deps,angular.json,pubspec.yaml,pyproject.tomlin the project tree - For each detected service, generate the codemap (see format below)
- 30% diff gate — if an existing codemap exists, run
git diff --statagainst the files it covers. If < 30% of covered files changed since last update → skip with note "No significant changes (< 30% diff)" - Write files to
docs/CODEMAPS/(create dir if missing) - Write diff summary to
.reports/codemap-diff.txt
Codemap Format
Each codemap file must follow this structure and stay under 1000 tokens:
# {Service} Codemap
**Updated:** {ISO-8601 date} **Stack:** {tech + version}
## Entry Points
- `{file}:{line}` — {one-line description}
## Key Modules / Features
- `{path}/` — {one-line description}
## Shared Utilities
- `{file}` — {one-line description}
## External Dependencies
- {dependency}: {how it's used}
## Data Flow
{1-3 line prose: request → service → DB pattern}
## Known Constraints
- {any non-obvious architectural decisions}
Example: Spring Boot Codemap
# Spring Boot API Codemap
**Updated:** 2026-03-29 **Stack:** Java 21 / Spring Boot 3.5.x / WebFlux / R2DBC
## Entry Points
- `src/main/java/.../Application.java:1` — SpringApplication entry
- `src/main/java/.../router/ApiRouter.java:20` — WebFlux functional route definitions
## Key Modules / Features
- `src/main/java/.../features/auth/` — JWT authentication, token validation
- `src/main/java/.../features/users/` — User CRUD, role management
## Shared Utilities
- `src/main/java/.../common/error/GlobalErrorHandler.java` — WebExceptionHandler
- `src/main/java/.../common/security/CorrelationIdFilter.java` — MDC tracing
## External Dependencies
- PostgreSQL (R2DBC): async reactive queries via R2dbcRepository
- Firebase Auth: token verification in JwtAuthFilter
## Data Flow
HTTP request → RouterFunction → Handler → Service → R2dbcRepository → PostgreSQL
All reactive — Mono/Flux all the way down, no blocking calls.
## Known Constraints
- No JPA — R2DBC only (reactive stack)
- WebFlux functional endpoints (not @Controller annotations)
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.
- 4d ago First seen · 105 lines · 0 tokens per session scan A 0e3337f6374c
update-codemaps is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,002 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 2026-09-03.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.