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 skills add cdeust/ai-architect-mcp --skill indexinggit clone --depth 1 https://github.com/cdeust/ai-architect-mcpWrote 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/skills/cdeust/ai-architect-mcp/indexing)<a href="https://agentmods.dev/skills/cdeust/ai-architect-mcp/indexing"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/indexing/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/skills/cdeust/ai-architect-mcp/indexing"><img src="https://agentmods.dev/badge/skills/cdeust/ai-architect-mcp/indexing.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 | $0.00004 | $0.00576 |
| Opus 5 | $0.00002 | $0.00288 |
| Sonnet 5 | $0.00001 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
codebase-indexing 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Indexing
Purpose
Index a repository to build the knowledge graph. Each phase is a separate tool call — if one fails, diagnose, fix, and continue without losing prior work.
When to Use
- First time analyzing a repository
- After significant code changes
- When codebase tools return stale or empty results
Tools (call in order)
Phase 1: Scan
ai_architect_codebase_scan(repo_path="/path/to/repo")
Returns: file count, language breakdown, total bytes.
If this fails: Check repo_path exists and is a git repository.
Phase 2: Parse + Resolve + Community + Process
ai_architect_codebase_parse(repo_path="/path/to/repo")
Returns: node count, relationship count, communities, processes.
If this fails: The scan succeeded so files exist. Check:
- tree-sitter grammar available for the language? Check language breakdown from scan.
- File too large? Default limit is 512KB — skip oversized files.
- Memory pressure? The 20MB chunk budget bounds per-chunk memory.
If community detection fails: Pipeline continues — communities are optional. Query/context/impact still work without communities.
If process detection returns 0: CALLS edges may have low confidence (< 0.5). This is expected for repos where most calls are cross-file fuzzy matches.
Phase 3: Store
ai_architect_codebase_store(repo_path="/path/to/repo")
Returns: db_path, db_size_mb, node/edge counts.
If this fails: SQLite write error — check disk space and permissions on .codebase-intelligence/ directory.
Convenience: Full Pipeline
ai_architect_codebase_analyze(repo_path="/path/to/repo")
Runs all 3 phases in sequence. Use when you don't need per-phase control.
After Indexing
Verify with:
ai_architect_codebase_query(query="main entry point")
If results are empty, the FTS index may not have built. Call store again.
Recovery Patterns
| Error | Action |
|---|---|
| "No files scanned" | Wrong repo_path. Check it's absolute and exists. |
| Parse returns 0 nodes | Language not supported or all files too large. Check scan language breakdown. |
| Store fails | Disk full or permissions. Check .codebase-intelligence/ is writable. |
| Query returns empty after index | FTS index didn't build. Re-run store. |
| Community count is 0 | leidenalg/igraph not installed. Install: pip install leidenalg python-igraph |
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.
- 9d ago First seen · 73 lines · 4 tokens per session scan A 9ec261b74312
codebase-indexing is a skill published in the GitHub repository cdeust/ai-architect-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 4 tokens to every session and 576 once invoked, about $0.0000 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 skills, from other repositories
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.