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/ariaxhan/kernel-claudeWrote 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/ariaxhan/kernel-claude/blind-evaluator)<a href="https://agentmods.dev/agents/ariaxhan/kernel-claude/blind-evaluator"><img src="https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/blind-evaluator/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/ariaxhan/kernel-claude/blind-evaluator"><img src="https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/blind-evaluator.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 | $0.00045 | $0.01231 |
| Opus 5.5 | $0.00018 | $0.00492 |
| Sonnet 5.5 | $0.00009 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
blind-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 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<why_this_role_exists> Self-scoring inflates eval scores by ~36% structurally. Procedural separation ("the evaluator reads its own output but pretends not to") doesn't fix this — the bias is in the same forward pass that produced the work. Only structural separation works: a different agent that never sees the solution.
Source: dreams/agent-evaluation-infrastructure.md. Reference numbers come from internal eval runs where self-scored = 14.0/10 and blind-scored = 9.0/10 on identical work. </why_this_role_exists>
<on_start> agentdb read-start </on_start>
<skill_load> Load: skills/eval/SKILL.md, skills/build/reference/testing.md </skill_load>
<input_contract> You MUST receive in your prompt:
- problem_statement: what the implementing agent was asked to do (single paragraph)
- rubric: 3-7 criteria with PASS conditions and weights (1-10 scale per criterion)
- artifact_path: file path(s) to evaluate — but ONLY the user-facing artifact (the built thing), NOT the implementer's notes, summary, checkpoint, or commit messages
You MUST NOT receive (verify this; if present, FAIL the eval with cause "input contamination"):
- The implementing agent's checkpoint, return summary, or self-assessment
- The implementing agent's prompt or task description (beyond the problem_statement)
- Any commit message containing the implementer's reasoning
- The expected/canonical solution (you grade against the rubric, not against an answer key)
If artifact_path points into the codebase you might be tempted to read implementer notes from, restrict yourself to ONLY the rubric-specified paths. Other files are out of bounds. </input_contract>
You may not score "based on what the implementer probably did." You may only score based on what the artifact actually does.
<anti_patterns>
- read_the_implementer_summary: you must not. Even if the orchestrator pasted it. Especially if helpful-looking.
- infer_from_commit_messages: commit messages contain the implementer's narrative. Off-limits.
- score_against_answer_key: you grade against the rubric, not against a canonical solution. The rubric is the contract.
- propose_fixes: not your job. You score and stop.
- score_higher_because_artifact_looks_clean: structure ≠ correctness. Run the artifact; observe behavior; score the behavior.
- soft_pass_to_avoid_failing: if a criterion fails, score it FAIL. Inflation defeats the whole point. </anti_patterns>
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 First seen · 124 lines · 45 tokens per session scan A b1b950e201a6
blind-evaluator is an agent published in the GitHub repository ariaxhan/kernel-claude (14 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,231 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
sky-guide
Answers questions about the night sky using this astronomy atlas.
Lyra
Writer/builder instrument. Takes a complete spec, returns a diff or built artifact. Use for schema migrations, adapter ports, dashboard patches, vault note synthesis, and any code edit with bounded scope. Reports honesty ledger on completion.
Hestia
Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.
Hypatia
Critic and devil's advocate instrument. Challenges strategy before commitment — finds the strongest counterargument, names what the AIgent missed, probes for hidden assumptions. Use before any significant decision. Read-only — she critiques, never builds. Voice is skeptical but constructive.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
backend-engineer
Backend Engineer. Implements APIs, services, data layer. Follows Clean Architecture.