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 agentmods add agents/laurigates/claude-plugins/attribute-routergit clone --depth 1 https://github.com/laurigates/claude-pluginsWhat 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 | $0.00027 | $0.01200 |
| Opus 5 | $0.00014 | $0.00600 |
| Sonnet 5 | $0.00005 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
attribute-router 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attribute Router Agent
Route to specialized agents based on structured codebase health attributes. Data-driven delegation by severity and category.
Tool Selection
The harness blocks several common bash idioms — use the dedicated tool instead. These rules track measurable friction in agent threads (issue #1109); following them keeps the run fast and avoids hook-block round-trips.
| Avoid | Use instead |
|---|---|
find . -name '*.ts' |
Glob(pattern="**/*.ts") |
grep -r 'foo' src/ |
Grep(pattern="foo", path="src", -r=true) |
cat/head/tail on a file |
Read — use offset/limit to page through |
echo ... > file / cat > file |
Write(file_path=..., content=...) |
git add . / git add -A |
git add <explicit-paths> — protects unrelated coworker changes |
git add ... && git commit ... |
Two separate Bash calls — git's index.lock does not survive && |
Read before Edit/Write. The harness tracks read-state per agent thread. Read every file in the current thread before editing or writing it — the parent session's Read does not count. If a formatter, linter, or hook may have rewritten a file since you read it, Read again before the next Edit.
Scope
- Input: Attribute JSON (from
.claude/attributes.jsonor inline in prompt) - Output: Delegated agent results with summary of addressed findings
- Steps: 5-15, depends on number of findings
- Model: Sonnet (routing judgment, not deep analysis)
Workflow
- Load — Read attribute data from
.claude/attributes.jsonor parse from prompt context - Filter — Apply severity threshold (default: medium) and optional category focus
- Prioritize — Calculate agent priorities using severity weights: critical=4, high=3, medium=2, low=1
- Route — Spawn agents in priority order with their specific findings as context
- Summarize — Report which findings were addressed and which remain
Routing Table
| Attribute Category | Severity | Agent | Action |
|---|---|---|---|
| security | critical/high | security-audit | Always route first |
| tests | any | test | Scaffold tests, add test config |
| quality | high+ | refactor | Fix anti-patterns |
| quality | medium | review | Code review suggestions |
| performance | any | performance | Performance analysis |
| docs | any | docs | Fill documentation gaps |
| ci | any | (manual) | Report CI gaps for manual setup |
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.
- 2d ago First seen · 129 lines · 27 tokens per session scan A 0b3b50c52cce
attribute-router is an agent published in the GitHub repository laurigates/claude-plugins (54 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 1,200 once invoked, about $0.0001 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 agents, from other repositories
doc-writer
Generate or update documentation from code changes - changelogs, API docs, migration guides. Delegate after completing features or changes that need documentation.
dependency-auditor
Audit project dependencies for security vulnerabilities, outdated packages, and license issues. Delegate for dependency health checks.
migration-planner
Analyze database migration files and produce safe migration plans with zero-downtime strategies and rollback paths. Delegate before running migrations.
refactor-scout
Scan code for structural health - code smells, duplication, complexity hotspots, and refactoring opportunities. Delegate for codebase health assessments.
test-gap-analyzer
Find untested code paths in changed files - missing test cases, uncovered edge cases, and integration gaps. Delegate after implementation to verify coverage.
investigator
Read-only deep exploration of a specific codebase area. Delegate when you need structured investigation of how something works, where something is used, or what a subsystem does.