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 elnonathan/semantic-js-mcp --skill semantic-navigationgit clone --depth 1 https://github.com/elnonathan/semantic-js-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/elnonathan/semantic-js-mcp/semantic-navigation)<a href="https://agentmods.dev/skills/elnonathan/semantic-js-mcp/semantic-navigation"><img src="https://agentmods.dev/badge/skills/elnonathan/semantic-js-mcp/semantic-navigation/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/elnonathan/semantic-js-mcp/semantic-navigation"><img src="https://agentmods.dev/badge/skills/elnonathan/semantic-js-mcp/semantic-navigation.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 | $0.00056 | $0.03875 |
| Opus 5 | $0.00028 | $0.01937 |
| Sonnet 5 | $0.00011 | $0.00775 |
| Haiku 4.5 | $0.00006 | $0.00387 |
Grade A, and why
semantic-navigation 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 5d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Navigation
Use semantic-js-mcp as static semantic evidence alongside text search, direct source inspection, dependency inspection, and focused tests.
Supported source extensions are .ts, .tsx, .mts, .cts, .js, .jsx, .mjs, .cjs, and .vue.
Choose The Smallest Useful Tool
| Starting information | Call | Provides | Continue with |
|---|---|---|---|
| Human selected a Codex project root | lsp_prepare_workspace_root |
Canonical path without access | Human confirmation, lsp_authorize_workspace_root |
| Human confirmed the prepared canonical root | lsp_authorize_workspace_root |
Process-lifetime workspace access | lsp_document_symbols |
| One file | lsp_document_symbols |
File structure | lsp_definition, lsp_audit_symbol |
| Partial symbol name | lsp_workspace_symbols |
Declaration discovery | lsp_count_named_symbol, lsp_audit_named_symbol |
| Exact source position | lsp_definition |
Resolved declaration | lsp_hover, lsp_count_references |
| Exact source position | lsp_hover |
Inferred type and documentation | lsp_definition, lsp_audit_symbol |
| One changed file | lsp_diagnostics |
Focused diagnostics | lsp_definition, lsp_hover |
| Exact callable position | lsp_call_hierarchy |
Bounded static incoming/outgoing call graph | lsp_call_hierarchy_page, direct source reading |
Existing callHierarchySetId |
lsp_call_hierarchy_page |
Later freshness-checked call edges | lsp_call_hierarchy_page, direct source reading |
| Exact symbol text, unknown scope | lsp_count_text_matches |
Text-match and file counts without semantic verification | lsp_count_named_symbol, lsp_audit_named_symbol |
| Exact symbol name, broad scope | lsp_count_named_symbol |
Small count response | lsp_audit_named_symbol, lsp_reference_page |
| Exact source position, broad scope | lsp_count_references |
Small count response | lsp_audit_symbol, lsp_reference_page |
| Exact symbol name, composed evidence | lsp_audit_named_symbol |
Compact definition, signature, counts, and freshness | lsp_reference_page |
| Exact source position, composed evidence | lsp_audit_symbol |
Compact definition, signature, counts, and freshness | lsp_reference_page |
| Exact source position, locations needed | lsp_references |
First verified-location page | lsp_reference_page |
Existing referenceSetId |
lsp_reference_page |
Later verified-location page | lsp_reference_page, lsp_definition |
Existing referenceSetId with unresolved candidates |
lsp_unresolved_reference_page |
Candidate locations and literal resolution reasons | lsp_unresolved_reference_page, lsp_definition |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · +4 lines eb7003571798
- 8d ago First seen · 202 lines · 56 tokens per session scan A ecc9bff0343f
semantic-navigation is a skill published in the GitHub repository elnonathan/semantic-js-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 56 tokens to every session and 3,875 once invoked, about $0.0003 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.