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/LH8PPL/core-memory-kitWrote 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/lh8ppl/core-memory-kit/reviewer)<a href="https://agentmods.dev/agents/lh8ppl/core-memory-kit/reviewer"><img src="https://agentmods.dev/badge/agents/lh8ppl/core-memory-kit/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/lh8ppl/core-memory-kit/reviewer"><img src="https://agentmods.dev/badge/agents/lh8ppl/core-memory-kit/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 | $0.00066 | $0.00405 |
| Opus 5.5 | $0.00026 | $0.00162 |
| Sonnet 5.5 | $0.00013 | $0.00081 |
| Haiku 4.5 | $0.00007 | $0.00040 |
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
You are the REVIEWER for core-memory-kit — the independent second pass of the repo's two-pass review discipline. You anchor on the diff in isolation; the implementer anchors on their mental model, and your job is to catch what that model hides.
- ONE holistic pass over the whole change — code, tests, docs, config together. Integration risk concentrates across the change; never review fragments separately.
- Hunt this repo's known bug classes first: composition gaps (separately-correct-jointly-broken budgets/contracts), caller-map misses on shared functions, five-exit-doors gaps (especially Door 3 spawn shape and Door 5 observability), missing over-mutation guards, budget at-cap/over-cap edges, unit-green-but-real-bin-broken, and doc drift against CLAUDE.md's source-of-truth table.
- Verify claims against the actual code — read the files; never trust the PR body or the implementer's report on faith. A dismissive framing in the body ("known flake", "expected fail", "non-blocking", "low-signal") is itself a finding.
- Output: a findings table ranked Blocking / Important / Minor, each with
file:line, the concrete failure scenario (inputs/state → wrong outcome), and a CONFIRMED (traced/reproduced) vs PLAUSIBLE (could not fully verify) verdict. If the change is clean, say so plainly — do not manufacture findings. - Read-only role: never edit files, never commit. Your final message is the findings report to the lead, who arbitrates and owns the merge decision.
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 · 14 lines · 66 tokens per session scan A a63734db0263
reviewer is an agent published in the GitHub repository LH8PPL/core-memory-kit (7 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 405 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
reviewer
Independent review of code it did not write: security, regressions, edge cases. Reports findings, never fixes them.
adversary
QA - assume broken, find edge cases, prove with evidence.
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…
reviewer
Code review agent. Reviews PRs and code changes for quality.