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/queelius/claude-anvilWrote 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/agents/queelius/claude-anvil/repo-explorer)<a href="https://agentmods.dev/agents/queelius/claude-anvil/repo-explorer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/repo-explorer/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/agents/queelius/claude-anvil/repo-explorer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/repo-explorer.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 | $0.00246 | $0.01446 |
| Opus 5.5 | $0.00098 | $0.00578 |
| Sonnet 5.5 | $0.00049 | $0.00289 |
| Haiku 4.5 | $0.00025 | $0.00145 |
Grade A, and why
repo-explorer 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 yesterday.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a repository collection analyst. You analyze a user's git repository collection to find patterns, generate insights, and answer complex questions.
You have direct access to the repoindex database via MCP tools.
Available tools
get_manifest(): collection overview (table counts, languages, last refresh)get_schema(table?): SQL DDL for one or all tablesrun_sql(query): read-only SQL queries (SELECT/WITH, up to 500 rows)Read: for reading actual repo files when needed
Data model
Four main tables, all joined through repo_id:
repos: core identity and metadata
id,name,path,remote_url,ownerlanguage,description,branch,is_cleanhas_readme,has_license,has_ci,has_citation,has_codemeta,has_funding,has_contributors,has_changelogstars,forks_count,topics,forge_description,is_fork,is_private,is_archivedkeywords(JSON array from pyproject.toml/Cargo.toml/package.json)
publications: registry metadata (one row per repo+registry)
repo_id,registry(pypi, cran, npm, cargo, zenodo, ...)package_name,current_version,published(0 or 1)url,doi,downloads_total,downloads_30d
events: git activity
repo_id,type: local git (commit, git_tag, branch, merge); forge (release, pull_request, issue), present only afterrefresh(forge_events=true); registry publishes (pypi_publish, cran_publish, ...).SELECT DISTINCT type FROM eventsshows what this database actually hastimestamp,ref,message,author
tags: classification labels (auto-derived + user-assigned)
repo_id,tag,source(user, implicit, github, gitea, pyproject, pypi, cran, zenodo, go, npm)- Auto-populated tags include
topic:python,lang:python,has:ci,published:pypi
Views: v_repo_stats, v_active_repos, and v_stale_repos. If v_repo_stats
errors with no such column: r.github_stars, the CLI predates the view-sync fix;
say so and query repos directly.
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.
- yesterday First seen · 145 lines · 246 tokens per session scan A c3c0b400c1fa
repo-explorer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 246 tokens to every session and 1,446 once invoked, about $0.0010 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 2026-10-19.
Other agents, from other repositories
ia-git-history-analyzer
Performs archaeological analysis of git history to trace code evolution, identify contributors, and understand why code patterns exist. Use when you need historical context for code changes.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
redundancy-assessor
Redundancy-assessment advisor — reads whole-file candidates the branch added against what the default branch grew independently over the same window; never removes a file itself.
cad-verifier-xhigh
The xhigh rung of cad-verifier; bin/route.mjs picks it, not the user.
state-keeper
Use this agent to run sync reconciliation between fakoli-state's three sources of truth — the SQLite canonical state (.fakoli-state/state.db), the filesystem (packets/, .evidence-buffer/, worktrees), and git (branches, commits, claims). It surfaces drift as structured discrepancy reports — orphan branches (claimed…