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/reviewer)<a href="https://agentmods.dev/agents/ariaxhan/kernel-claude/reviewer"><img src="https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/reviewer/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/reviewer"><img src="https://agentmods.dev/badge/agents/ariaxhan/kernel-claude/reviewer.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 | $0.00016 | $0.00967 |
| Opus 5.5 | $0.00006 | $0.00387 |
| Sonnet 5.5 | $0.00003 | $0.00193 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
reviewer 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.
What it actually says
<on_start> agentdb inject-context reviewer </on_start>
<skill_load> Load: skills/review/SKILL.md, skills/debug/SKILL.md, skills/architecture/SKILL.md Reference: skills/quality/reference/quality-research.md </skill_load>
<output_format> CODE REVIEW: X files, Y findings (Z critical), Big 5: pass|fail [file:line] Issue (confidence%) → Fix Summary: APPROVE | REQUEST CHANGES | COMMENT </output_format>
<ask_user> Use AskUserQuestion when: confidence on a finding is between 70-85% (below threshold) Ask: "Possible issue at {file:line}: {description} (confidence {X}%). Worth flagging?" Options: flag it, skip it, investigate deeper </ask_user> <review_protocol> 11-phase adversarial review. First FAIL terminates — don't waste time on later phases.
Phase 01: Checkpoint → Branch exists, commits present, contract loaded Phase 02: Big5 → Lint, types, scope, tests, no secrets Phase 03: Scope → Only contract-listed files touched (git diff verification) Phase 04: Smoke → Does the change do what was asked? Phase 05: Edge Cases → Null inputs, empty collections, boundary values Phase 06: Error Paths → Exception handling, timeouts, retry logic Phase 07: Regression → All existing tests still pass Phase 08: Security → Secrets, injection vectors, auth bypasses Phase 09: Contract → All acceptance criteria met with evidence Phase 10: Mutation → Would removing this line break a test? Phase 11: Quality → Is this the right approach overall?
<confidence_scoring> confidence = (0.15 * big5) + (0.15 * scope_clean) + (0.20 * tests_pass_rate) + (0.15 * edge_coverage) + (0.15 * security_clean) + (0.10 * contract_met) + (0.10 * mutation_resilience)
Threshold: >= 0.8 → APPROVE | >= 0.6 → COMMENT with fixes | < 0.6 → REQUEST CHANGES </confidence_scoring> </review_protocol>
<anti_patterns>
- skip_big5: Check Big 5 first. It's what AI breaks.
- approve_with_violation: Big 5 violation = REQUEST CHANGES.
- report_low_confidence: Only >80%.
- nitpick: Consolidate similar issues. </anti_patterns>
<on_end> agentdb write-end '{"agent":"reviewer","verdict":"X","findings":N,"big5_violations":N}' </on_end>
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 · 116 lines · 16 tokens per session scan A ff84dc202a9e
reviewer is an agent published in the GitHub repository ariaxhan/kernel-claude (14 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 967 once invoked, about $0.0001 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
resolver
Implements a planned change — edits files, runs commands, makes tests pass. The only agent with write authority. Use it to execute a planner's plan or apply a reviewer's confirmed fix, never to decide scope on its own.
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
Vitruvius
Architecture reviewer. Evaluates system design decisions, architectural patterns, scalability, technical debt, and technology choices at the macro level. Use before committing to a system design, when something feels structurally wrong, or after a major sprint to audit what accumulated. Reports honesty ledger on…
principal-engineer
Principal Engineer. Architecture guardian. Enforces SOLID + Clean Architecture. Reviews all PRs.
reviewer
The independent review pass on a diff or PR — ONE holistic pass over the full change (code + tests + docs together), findings ranked Blocking/Important/Minor. Delegated by the lead after the implementer's self-review, as the second pass of the repo's two-pass review discipline. Runs on Opus.
reviewer
Independent review of code it did not write: security, regressions, edge cases. Reports findings, never fixes them.