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 commands/jsungmin/vs-token-safer/dcegit clone --depth 1 https://github.com/JSungMin/vs-token-saferWrote 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/commands/jsungmin/vs-token-safer/dce)<a href="https://agentmods.dev/commands/jsungmin/vs-token-safer/dce"><img src="https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/dce.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 | $0.00036 | $0.00997 |
| Opus 5 | $0.00018 | $0.00498 |
| Sonnet 5 | $0.00007 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
dce scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vs-token-safer — dead-code elimination (preview only)
Use this when the user wants to know what code can be safely removed starting from one or more symbols
("is Foo used anywhere?", "what becomes dead if I delete Foo?", "find unused code reachable from here").
Run it with the seed symbol(s). Prefer the vts_admin MCP tool (server vs-search):
vts_admin { "op": "dce", "params": { "seed": "Foo", "projectPath": "<the project root>" } }
For several seeds use "seeds": "Foo,Bar,Baz". Prefer the MCP tool — it runs in the warm server process, and
vts is often not on PATH in Bash. If the vs-search server is unavailable, run the bundled CLI:
node "$CLAUDE_PLUGIN_ROOT/server/cli.js" dce --seed Foo --projectPath <root>
# (if vts is on PATH: vts dce --seeds Foo,Bar,Baz --projectPath <root> [--entry main,registerPlugin --maxNodes 120])
Warm-index requirement (C++/clangd)
For a clangd (C/C++) project the call graph must be warm — a cold or large tree (e.g. an Unreal monorepo,
~26k TUs) under-reports callers, so a live symbol could look DEAD. dce therefore refuses on a cold clangd
index and tells you to build one. Indexing the whole tree is heavy, so scope it first:
vts setup --scope Source --projectPath <root> # narrow to the module subtree, not the whole monorepo
vts preindex --projectPath <root> # build the scoped index (or keep the MCP server warm)
Then re-run dce. To inspect the structure on a cold index anyway, pass allowCold=true — every verdict is
then forced to INCONCLUSIVE (nothing is ever marked DEAD). TypeScript/Python/C# index on open and are not gated.
Then show the output verbatim. It classifies every symbol reachable from the seeds as:
- DEAD — no live caller remains; listed in a safe deletion order (top is removable first).
- HELD — still referenced; not dead (shows who calls it).
- ENTRY — a root kept on purpose (main / public API / a name you passed via
--entry). - INCONCLUSIVE — could not be resolved, or its caller set could not be proven complete.
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 · 68 lines · 36 tokens per session scan A e851c79d398a
dce is a command published in the GitHub repository JSungMin/vs-token-safer (11 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 997 once invoked, about $0.0002 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 commands, from other repositories
rp-build-cli
Build with rp-cli context builder → chat → implement.
review
Review current changes for correctness, style, and potential issues.
index
Visual overview of Beacon index — chunks, coverage, provider. Pass --files to list indexed files.
codesage-reindex
Force an incremental codesage re-index (use when git hooks didn't fire). Auto-cleans orphan vec tables if the config model has changed.
codesage-bench
Run CodeSage retrieval benchmarks on all corpora, save timestamped scorecards, print a summary.
cb-search
코드브레인 BM25 검색 — stale 자동 refresh.