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/jghiringhelli/codeseekerWrote 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/jghiringhelli/codeseeker/relationships)<a href="https://agentmods.dev/commands/jghiringhelli/codeseeker/relationships"><img src="https://agentmods.dev/badge/commands/jghiringhelli/codeseeker/relationships/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/jghiringhelli/codeseeker/relationships"><img src="https://agentmods.dev/badge/commands/jghiringhelli/codeseeker/relationships.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 | $0.00000 | $0.00472 |
| Opus 5.5 | $0.00000 | $0.00189 |
| Sonnet 5.5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
relationships 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
Explore Code Relationships
Explore dependencies and relationships for a file or code pattern.
Arguments:
$ARGUMENTS- File path or search query to explore relationships for
What this does:
- Traverses the knowledge graph built from AST-parsed imports
- Shows import/export chains, class hierarchies, call relationships
- Follows edges in either direction
Instructions for Claude:
CodeSeeker exposes a single MCP tool, mcp__codeseeker__codeseeker, routed by action.
-
If
$ARGUMENTSlooks like a file path, seed the traversal with it:{ "action": "graph", "project": "<absolute path of the project root>", "graph": { "seed": "$ARGUMENTS", "depth": 1, "dir": "both", "max": 50 } } -
If
$ARGUMENTSis a search term, let CodeSeeker find the seeds semantically:{ "action": "graph", "project": "<absolute path of the project root>", "graph": { "q": "$ARGUMENTS", "depth": 1 } } -
Useful options:
graph.depth: 1–3. Depth 2 finds cross-file chains but leaks scope on broad queries.graph.rel: filter edge types —imports,exports,calls,extends,implements,contains,uses,depends_ongraph.dir:"in"(who depends on this),"out"(what this depends on),"both"
-
To look up a single symbol rather than traverse from a file, use
action: "sym":{ "action": "sym", "project": "<root>", "sym": { "name": "UserService" } } -
Present the result as a dependency tree: what imports this, what this imports, related classes and functions.
Note on accuracy: import edges are static and reliable; call edges use regex heuristics, so dynamic dispatch, callbacks, and event handlers are not detected.
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 Changed · +21 lines cb5985853b2e
- 1mo ago First seen · 30 lines · 0 tokens per session scan A c55072714e8a
relationships is a command published in the GitHub repository jghiringhelli/codeseeker (20 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 472 tokens. 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
performance-optimization
Orchestrate end-to-end application performance optimization from profiling to monitoring.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
config-validate
Validate application configuration with schemas, per-environment rules, runtime checks, and secure handling of sensitive values.
smart-debug
AI-assisted smart debugging — parse error messages, stack traces, and failure patterns to identify root causes and produce a fix with automated observability steps.
team-debug
Debug issues using competing hypotheses with parallel investigation by multiple agents.
reproduce-bug
Reproduce and investigate a bug using logs, console inspection, and browser screenshots.