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.
git clone --depth 1 https://github.com/dvcdsys/code-indexWrote 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/dvcdsys/code-index/refs)<a href="https://agentmods.dev/commands/dvcdsys/code-index/refs"><img src="https://agentmods.dev/badge/commands/dvcdsys/code-index/refs/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/commands/dvcdsys/code-index/refs"><img src="https://agentmods.dev/badge/commands/dvcdsys/code-index/refs.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 | $0.00017 | $0.00113 |
| Opus 5.5 | $0.00007 | $0.00045 |
| Sonnet 5.5 | $0.00003 | $0.00023 |
| Haiku 4.5 | $0.00002 | $0.00011 |
Grade A, and why
refs 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 1mo 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.
What it actually says
Find references to the symbol $ARGUMENTS in the cix index:
cix references $ARGUMENTS
Group the references by file and call out any high-traffic call sites or
suspicious usage patterns. If you need fewer results, add --limit 20.
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.
- 1mo ago First seen · 15 lines · 17 tokens per session scan A c23946c2f769
refs is a command published in the GitHub repository dvcdsys/code-index (30 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 113 once invoked, about $0.0001 per session on Opus 5.5. 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
definition
Find where a symbol is defined in the codebase.
local
Command "local" from getsentry/toolkit, covering examples, start the server and tail events (default), run your app with the local server auto-enabled, use a custom port and only show errors and logs (filter out transactions).
poly-check
Lint and check formatting with poly — apply no fixes; summarize findings and drift.
debug-files
Command "debug-files" from getsentry/toolkit, covering examples, inspect a debug information file (auto-detects the format), bundle jvm sources with a debug id, exclude additional directories and output as json.
release
Command "release" from getsentry/toolkit, covering examples, list releases (auto-detect org), list releases in a specific org, view release details and create and finalize a release.
perf-profile.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.