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 skills/bug-ops/zeph/code-analysisnpx skills add bug-ops/zeph --skill code-analysisgit clone --depth 1 https://github.com/bug-ops/zephWhat 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 | $0.00105 | $0.02172 |
| Opus 5 | $0.00053 | $0.01086 |
| Sonnet 5 | $0.00021 | $0.00434 |
| Haiku 4.5 | $0.00011 | $0.00217 |
Grade A, and why
code-analysis 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 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.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Analysis with LSP
Use LSP tools for accurate, compiler-verified code understanding. These tools require the mcpls
MCP server to be configured.
Positions
Positions are 1-based: line 1, column 1 is the first character. If you read a file and see line numbers in the output, use those directly — no conversion needed (mcpls translates to 0-based LSP positions internally).
File paths must be absolute. Relative paths will not resolve correctly.
Tool Reference
Code Intelligence
| Tool | Purpose | When to use |
|---|---|---|
get_hover |
Type signature, inferred type, and documentation at a position | "What type is X?", "What does this function do?" |
get_definition |
Navigate to where a symbol is defined | Read a function/type implementation before reasoning about it |
get_references |
Find all usages of a symbol across the workspace | Before renaming, deleting, or changing a symbol's signature |
get_completions |
Context-aware suggestions respecting types and scope | Exploring unknown APIs, discovering available methods |
get_document_symbols |
Structured outline of a file (functions, types, constants, fields) | Understanding file structure without reading every line |
workspace_symbol_search |
Search for a symbol by name across the entire workspace | Know a name but not which file defines it |
Diagnostics and Correctness
| Tool | Purpose | When to use |
|---|---|---|
get_diagnostics |
Real compiler errors and warnings for a file | After editing code — always call to verify correctness |
get_cached_diagnostics |
Previously cached diagnostics (no fresh check) | Quick check when file has not changed recently |
get_code_actions |
Quick fixes, refactorings, source actions at a position | Fix diagnostics automatically, add missing imports |
Refactoring
| Tool | Purpose | When to use |
|---|---|---|
rename_symbol |
Workspace-wide rename with full reference tracking | Always prefer over manual find-and-replace |
format_document |
Apply language-specific formatting rules | After editing, before committing |
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 · 200 lines · 105 tokens per session scan A 21c3c46ecd01
code-analysis is a skill published in the GitHub repository bug-ops/zeph (57 stars, last pushed 7d ago), licensed MIT. It adds 105 tokens to every session and 2,172 once invoked, about $0.0005 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
verify
Run Chimeraforge's canonical verification gate end-to-end and report the real output before claiming work done or committing. Failing output gets pasted, fixed, and re-run — never summarized away.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
greptimedb-release
Runbook for publishing a new GreptimeDB version (tag + GitHub release + docs release-note PR) on the upstream GreptimeTeam/greptimedb repo. Use when asked to "release" / "publish" a GreptimeDB version (e.g. v1.1.0, v1.0.3).