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/devonmorris/claude-ctags/ctags-usagenpx skills add DevonMorris/claude-ctags --skill ctags-usagegit clone --depth 1 https://github.com/DevonMorris/claude-ctagsWrote 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/devonmorris/claude-ctags/ctags-usage)<a href="https://agentmods.dev/skills/devonmorris/claude-ctags/ctags-usage"><img src="https://agentmods.dev/badge/skills/devonmorris/claude-ctags/ctags-usage.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 | $0.00086 | $0.01263 |
| Opus 5 | $0.00043 | $0.00632 |
| Sonnet 5 | $0.00017 | $0.00253 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade B, and why
ctags-usage scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep "^SymbolName " .claude/tags How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ctags Usage for Efficient Code Navigation
Overview
This plugin maintains a ctags index at .claude/tags that maps symbol names to their locations. The index includes both definitions and references, making it useful for finding where symbols are defined AND where they are used. Use this index for efficient code navigation with minimal token usage instead of running broad grep or tree searches.
When to Use Ctags
Use ctags lookup FIRST when:
- Finding where a class, function, method, or type is defined
- Finding references to a symbol (where it's used, imported, called)
- Navigating to a symbol's source location
- The user asks "where is X defined?" or "find references to X"
Fall back to grep when:
- Searching for text patterns that aren't symbol names
- Searching for string literals, comments, or documentation
- The ctags lookup returns no results
- Searching in file types not indexed by ctags
How to Query the Tags Index
Direct Tags File Query
Query the tags file using grep for the symbol name:
grep "^SymbolName " .claude/tags
The tags file format is tab-separated:
symbol_name<TAB>file_path<TAB>pattern_or_line<TAB>kind
Using the Query Script
For cleaner output with file:line format:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/query-tags.sh SymbolName
Returns results like:
src/services/user.ts:42
src/models/user.ts:15
Interpreting Results
- Multiple results indicate the symbol appears in multiple places (definitions AND references)
- Use the
kindfield to distinguish:c= class,f= function,m= method,v= variable (definitions)r= reference (where the symbol is used/imported/called)
- Filter by kind to narrow results:
grep "^Symbol\t" .claude/tags | grep "kind:r"for references only - Read the specific file at the returned line number
Token Efficiency Strategy
Before (Inefficient)
User: "Where is UserService defined?"
Step 1: grep -r "UserService" .
Result: 50 lines (imports, usages, comments, definition)
Tokens: ~2000
Step 2: Read several files to find the actual definition
Tokens: ~3000 more
Total: ~5000 tokens
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 · 192 lines · 86 tokens per session scan B d6b014122b4f
ctags-usage is a skill published in the GitHub repository DevonMorris/claude-ctags (15 stars, last pushed 7mo ago), licensed MIT. It adds 86 tokens to every session and 1,263 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…