Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dualeai/seeknpx agentmods add skills/dualeai/seek/seek-searchWrote 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/dualeai/seek/seek-search)<a href="https://agentmods.dev/skills/dualeai/seek/seek-search"><img src="https://agentmods.dev/badge/skills/dualeai/seek/seek-search/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/dualeai/seek/seek-search"><img src="https://agentmods.dev/badge/skills/dualeai/seek/seek-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00847 |
| Opus 5 | $0.00026 | $0.00424 |
| Sonnet 5 | $0.00010 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
seek-search 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search code with seek
seek ranks results by relevance and returns them grouped by file with context
and symbol tags. Use it wherever you would otherwise reach for grep, ripgrep,
git grep, or find.
seek [flags] '<query>' [path...]
Query filters
All filters go inside ONE quoted argument. Paths come after it.
| Filter | Finds |
|---|---|
sym:Name |
definitions - functions, classes, methods (ctags) |
content:REGEX |
a regex match in file content |
file:path |
paths matching a substring |
-file:path |
paths NOT matching a substring |
lang:go |
one language |
type:file |
filenames only, no content |
Bare words are matched independently and combined with AND: seek 'parse token'
returns files containing both.
Flags
| Flag | Effect |
|---|---|
-n N |
at most N files (0 = unlimited) |
-m N |
at most N matches per file (0 = unlimited) |
-A N |
N lines after each match (0-512) |
-C N |
N lines before and after each match (0-512) |
Flags go before the query. Do not combine -A and -C.
Examples
seek 'sym:executeParsedSearchScoped' # where is this defined
seek 'sym:Index file:index -file:test' # definitions, excluding tests
seek 'content:func.*Test lang:go -file:bench'
seek 'type:file config' # config-ish filenames
seek 'TODO' ./cmd ./docs # limit to two subtrees
seek -n 5 'retry backoff' # top 5 files only
seek -n 5 -m 1 -A 20 'sym:executeParsedSearchScoped' ./cmd/seek
Paths
With no path, seek searches the current Git worktree. Path operands accept
directories or exact files, inside or outside the worktree, and can be mixed in
one call. Across roots, headers show the absolute path and a [git]/[folder]
tag so every match is directly openable.
Path operands constrain what Seek indexes. file: and -file: query filters
apply to results after indexing and do not reduce index limits.
Pitfalls
- One quoted argument for filters.
seek 'sym:Foo file:bar', notseek sym:Foo file:bar. - Single quotes, so the shell does not expand
|,(,). - Flags before the query:
seek -n 5 'Foo' ./cmd. - Paths after the query are path operands, not filters.
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.
- 9d ago First seen · 90 lines · 51 tokens per session scan A 9339adf85bee
seek-search is a skill published in the GitHub repository dualeai/seek (37 stars, last pushed 13d ago), licensed Apache-2.0. It adds 51 tokens to every session and 847 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…