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 sverklo/sverklo --skill sverklo-skillgit clone --depth 1 https://github.com/sverklo/sverkloWrote 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/sverklo/sverklo/sverklo-skill)<a href="https://agentmods.dev/skills/sverklo/sverklo/sverklo-skill"><img src="https://agentmods.dev/badge/skills/sverklo/sverklo/sverklo-skill/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/sverklo/sverklo/sverklo-skill"><img src="https://agentmods.dev/badge/skills/sverklo/sverklo/sverklo-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.01516 |
| Opus 5 | $0.00014 | $0.00758 |
| Sonnet 5 | $0.00005 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
Sverklo Code Intelligence 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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sverklo Code Intelligence Skill
Sverklo is a local-first code intelligence MCP server. It gives you a dependency graph, semantic search, blast-radius analysis, and risk-scored PR review — all running on the user's machine. No API keys, no cloud, no data leaves the laptop.
Setup (one time per project)
npm install -g sverklo
cd /path/to/project
sverklo init
sverklo init auto-detects the user's AI editor (Claude Code, Cursor, Windsurf, etc.), writes the MCP config, appends sverklo instructions to CLAUDE.md, and verifies the setup. Safe to re-run.
If something looks wrong after setup:
sverklo doctor
Once installed, sverklo tools appear as MCP tools prefixed with sverklo_. The index builds automatically on first use.
When to use Sverklo vs Grep vs Read
Use Sverklo when:
- You don't know exactly what to search for ("where is auth handled?")
- You need to understand importance or ranking ("what are the key files?")
- You need blast-radius analysis ("what breaks if I rename this?")
- You need to prove code is dead ("is this function actually called?")
- You're reviewing a diff and need risk scoring
Use Grep when:
- You need exact string matching ("does
FEATURE_FLAG_Xexist?") - You know the literal identifier and just want its location
Use Read when:
- You need to see file contents (sverklo is not a file reader)
Skip sverklo for codebases under ~50 source files — the overhead doesn't pay off. Just read everything directly.
Tools Reference
1. sverklo_search — Semantic code search
Hybrid BM25 + vector + PageRank search. Use instead of Grep when you don't know the exact string.
sverklo_search query:"authentication middleware" top_k:5
Returns ranked code chunks with file paths, line numbers, and relevance scores. Results are ordered by structural importance (PageRank), not just text similarity.
When to reach for it: "Where is X handled?", "Find the code that does Y", any exploratory search where you'd otherwise grep for 10 different terms.
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.
- 12d ago First seen · 156 lines · 27 tokens per session scan A 5525b975094e
Sverklo Code Intelligence is a skill published in the GitHub repository sverklo/sverklo (79 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 1,516 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 2026-08-30.
Other skills, from other repositories
cartograph
Explore a codebase through Cartograph v2's PostgreSQL code graph: intent-aware context, exact/BM25/hybrid search, callers/callees/impact, affected tests, live source, review, freshness, and bounded index administration.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
lsp-inspect
Full code quality audit for a file, package, or directory. Supports batch mode (directory walk with --top ranking), comparison mode (--diff for branch-only issues), severity calibration by blast radius, fix suggestions, and confidence tiers. Applies a check taxonomy (dead symbols, silent failures, error wrapping…
lsp-dead-code
Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.