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 HumanBean17/jrag --skill explore-codebase-cligit clone --depth 1 https://github.com/HumanBean17/jragWrote 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/humanbean17/jrag/explore-codebase-cli)<a href="https://agentmods.dev/skills/humanbean17/jrag/explore-codebase-cli"><img src="https://agentmods.dev/badge/skills/humanbean17/jrag/explore-codebase-cli/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/humanbean17/jrag/explore-codebase-cli"><img src="https://agentmods.dev/badge/skills/humanbean17/jrag/explore-codebase-cli.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 | $0.00129 | $0.03152 |
| Opus 5.5 | $0.00052 | $0.01261 |
| Sonnet 5.5 | $0.00026 | $0.00630 |
| Haiku 4.5 | $0.00013 | $0.00315 |
Grade A, and why
explore-codebase-cli 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Principles
- Smallest sufficient tool — both ways. Pick the lightest tool that answers the question. Don't run
jrag impactwhenjrag callerssuffices; don't firejrag inspectwhen a singleGreplands on the line; don'tGrepthe whole repo whenjrag find --role CONTROLLER --service Slists them structurally. Graph beats grep for structural questions; grep beats graph for raw text, config, and a stale index. Neither is the default — match the tool to the question. - Excerpts over dumps. Read excerpts and relevant sections, not entire files. Summarize findings.
- Stop when answered. Don't prefetch unrelated subgraphs or scan unrelated directories.
Tool Inventory
jragCLI — navigate & search: one command per intent — graph navigation (callers,callees,hierarchy,implementations,dependents,impact,flow,http-routes,http-clients,producers,topics,overview),search(locate code or config by meaning, keywords, or natural language), andfind/inspect(resolve identifiers; list nodes by role/kind). Drives the same index as the MCP server. Fast path for structural questions (call chains, route handlers, HTTP/async seams, clients/producers, service boundaries, impact, FQN resolution, implementations, DI chains) and fuzzy discovery alike. Pass it names (FQN / simple name / route path / topic) — it resolves internally; raw node IDs are never required. Requires an index; if unindexed every command exits 2 (see jrag surface).- File-system:
Grep(content/regex),Glob(name/path patterns),Read(offset/limit). First-class for text searches, file discovery, and anything outside the graph index (config, build, test, CI, docs) — and the right answer whenever they're lighter than ajragcall. - Other:
Bash(read-only:git log,git blame,ls,find),WebSearch/WebFetch.
CLI surface only — don't also drive the MCP tools (search/find/describe/neighbors/resolve) in the same session; the two vocabularies conflict.
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 ad31da0e1f88
- 1mo ago Changed 0d670eca6f9c
- 1mo ago First seen · 108 lines · 129 tokens per session scan A 6fe3addded09
explore-codebase-cli is a skill published in the GitHub repository HumanBean17/jrag (9 stars, last pushed 22d ago), licensed MIT. It adds 129 tokens to every session and 3,152 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
kmp-lsp
Kotlin/Java/Swift LSP server for code navigation in Android and iOS codebases. Use when navigating Kotlin, Java, or Swift source files: finding class definitions, listing symbols, jumping to implementations, finding all usages, checking type signatures, or switching workspace between projects. Triggers for: "find this…
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
shaft-accessibility-testing
Use when testing web or mobile accessibility for WCAG conformance, keyboard and focus behavior, semantics, errors, or user impact.
architect
Run /architect when choosing between approaches, designing a feature or page, picking a tech stack, or when /develop says a decision is owed, anytime a load bearing technical decision is unmade. Asks deep questions, recommends an answer, and writes a build spec to docs/specs/. Owns all spec files.
xcode-workflows
Xcode build system guidance for xcodebuild operations. Use when building iOS projects, running tests, analyzing build failures, or configuring schemes. Covers build/clean/test operations, interpreting xcodebuild output, and troubleshooting common build errors.
scope
Run /scope to turn a product idea into a living, coarse scope in docs/scope/ and keep it current: plan a new product, plan the next slice, enroll one named feature, or run with no argument to reconcile after shipping and queue what is next. Seeds WHAT to build; /architect designs, /develop builds.