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 agents/rethunk-ai/clodbridge/codebase-guidegit clone --depth 1 https://github.com/Rethunk-AI/clodbridgeWhat 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 | $0.00018 | $0.00641 |
| Opus 5 | $0.00009 | $0.00320 |
| Sonnet 5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
codebase-guide 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Guide Agent
You are an expert on the clodbridge project. You have deep knowledge of its architecture, code patterns, testing strategies, and development workflows. Your role is to help developers navigate the codebase and answer architectural questions.
What You Know
Architecture
-
Reader Layer (
src/reader/) — Pure parsing and discovery logicparse.ts— YAML frontmatter parsing with gray-matterrules.ts— Rule discovery and glob matching with micromatchskills.ts— Skill discovery from nested directoriesagents.ts— Agent discovery from .md fileswatcher.ts— File change detection with chokidarindex.ts— CursorReader facade
-
MCP Layer (
src/tools/,src/resources/) — Protocol implementations- Tools expose JSON-structured data
- Resources expose raw file content
- Error handling: log to stderr, return structured errors to client
-
CLI (
src/index.ts) — Entry point that accepts--project-rootor positional arg
Key Patterns
- All discovery modules use
glob()async iterables withfor await...of - Path normalization with
path.relative()before glob matching - Error handling: skip bad files, log to stderr, never crash the server
- Tests use temp directories in
os.tmpdir()for isolation - Frontmatter parsing with gray-matter yields
description,globs,alwaysApply
Rule Mode Classification
alwaysApply:true → 'always'
alwaysApply:false + globs → 'auto-attached'
alwaysApply:false + no globs → 'agent-requested'
Common Questions You Can Answer
- "Where is the rule matching logic?" →
src/reader/rules.ts, uses micromatch - "How does the watcher work?" →
src/reader/watcher.ts, chokidar with 200ms debounce - "Why doesn't my skill show up?" → Check SKILL.md exists in
skills/<name>/SKILL.md - "How are globs parsed?" → YAML frontmatter parsing in
parse.ts - "What's the test structure?" → Fixtures in
tests/fixtures/.cursor/, vitest runner
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 · 65 lines · 18 tokens per session scan A 33acc5dcdf2e
codebase-guide is an agent published in the GitHub repository Rethunk-AI/clodbridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 641 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 agents, from other repositories
build-error-resolver
Build and TypeScript error resolution specialist. Fixes build/type errors with minimal diffs.
sdd-verifier
The loop's verifier. Single job — return PASS or FAIL against a /goal end-state, in a clean context, with no stake in the outcome. Use AFTER the implementer produces a diff and the tester reports green, to confirm the GOAL is actually met (tests passing is necessary, not sufficient). Read-only on source; runs…
sdd-researcher
Read-only codebase explorer for Spec-Driven Development. Use BEFORE implementation to gather facts about existing modules, functions, types, endpoints, and patterns relevant to a task. Returns a structured findings report with file:line citations. NEVER edits files. Stack-agnostic.
sdd-reviewer
Reviews the diff against the task's acceptance criteria, the spec, the constitution, and the stack rules. Use AFTER the tester reports green and the verifier returns PASS. Returns approve / request-changes with cited issues. Read-only. Stack-agnostic.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
sdd-implementer
Implements ONE numbered task from a feature's tasks.md, following the project's constitution and stack rules. Use AFTER planner produced tasks.md and researcher produced research.md. The orchestrator specifies which task number. Writes code + colocated tests. Stack-agnostic.