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/florianbruniaux/claude-code-ultimate-guide/output-evaluatorgit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-ultimate-guideWhat 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 | $0.00022 | $0.01015 |
| Opus 5 | $0.00011 | $0.00508 |
| Sonnet 5 | $0.00004 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
output-evaluator 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
Licensed CC-BY-SA-4.0
The repository is licensed CC-BY-SA-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 144 lines · 22 tokens per session scan A 96af65072649
output-evaluator is an agent published in the GitHub repository FlorianBruniaux/claude-code-ultimate-guide (5,863 stars, last pushed today), licensed CC-BY-SA-4.0. It adds 22 tokens to every session and 1,015 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
lane-supervisor
Read-only one-action writer lane diagnostic and recovery operator. Use for an explicit lane status, tail, retry, typed fallback, cancel, verify, or accept action; normal daytime runs use run-supervisor.
lane-critic
Lane plan-critique compressor. Coverage auditor only — owns/verify gaps. No product edits. Use for stages.plancritique when provider is opencode.
docs-maintainer
Nightly/INIT docs refresh (shell-out to Codex Luna max fast). No feature code.
run-supervisor
Daytime run supervisor. Starts and visibly watches one durable deterministic run controller until every writer lane is accepted or the run is blocked. Use proactively for multi-lane work, параллельные задачи, запусти и следи, доведи run до конца.