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/fazxes/claude-code/comparatorgit clone --depth 1 https://github.com/fazxes/Claude-codeWrote 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/fazxes/claude-code/comparator)<a href="https://agentmods.dev/agents/fazxes/claude-code/comparator"><img src="https://agentmods.dev/badge/agents/fazxes/claude-code/comparator.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01762 |
| Opus 5 | $0.00000 | $0.00881 |
| Sonnet 5 | $0.00000 | $0.00352 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
comparator 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 203 lines · 0 tokens per session scan A fe1fc9787c49
comparator is an agent published in the GitHub repository fazxes/Claude-code (234 stars, last pushed 5mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 1,762 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 2026-09-03.
Other agents, from other repositories
nimbus-ci-doctor
Use when a Nimbus PR's CI is red and you need to root-cause the failures instead of push-and-see guessing. Pulls the failed CI job logs via gh, diagnoses against the known CI-only traps (frozen-lockfile drift, cross-platform URL/path flakes, mock.module leaks, gitleaks full-history, the pr-quality fail-fast SIGTERM)…
nimbus-coverage-floor
Use when a PR is failing (or might fail) the Nimbus true-coverage ratchet — the per-file coverage floor enforced by audit:coverage-floor (≥85% line AND ≥80% branch; two separate constants, FLOORPCT / BRANCHFLOORPCT). Drives the file to green: runs the Docker-Linux-authoritative lcov build, reads the exact violations…
nimbus-sonar-gate
Use when the SonarCloud quality gate is failing (or to audit it) on a Nimbus PR — it is the BLOCKING quality gate (CI gates on it). Queries the gate + issues + hotspots via the SonarCloud API, applies fix-not-exclude code fixes for real issues, and for genuine false-positives / safe security hotspots marks them with a…
nimbus-preflight-guard
Use right before pushing a Nimbus branch to catch what CI would reject — so red never reaches CI and you avoid the push-and-see ping-pong. Runs the memory-safe static gates, scoped tests for changed files, the static structure audits, and (when coverage/connectors/migrations are touched) the Docker-Linux dry-run, then…
AGENTS
Agent "AGENTS" from l-agence/agence, covering agence agents: quick reference, 1. aider, → generates patch → applies via aider cli, 2. chad and that's a right dog's dinner. batch 'em up...
ROUTING
Agent "ROUTING" from l-agence/agence, covering agence model routing reference (v0.3.0), routing layers (precedence, highest first), operational modes (agenceroutermode), blastradius — code mode sub-tiers (agenceblastradius, v0.5) and @provider.tier routing hint syntax.