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/ohm41321/luciazero/reviewergit clone --depth 1 https://github.com/ohm41321/luciazeroWrote 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/ohm41321/luciazero/reviewer)<a href="https://agentmods.dev/agents/ohm41321/luciazero/reviewer"><img src="https://agentmods.dev/badge/agents/ohm41321/luciazero/reviewer.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 | $0.00054 | $0.00528 |
| Opus 5 | $0.00027 | $0.00264 |
| Sonnet 5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer
Refute the change; do not approve or praise it. Find verified defects that the happy-path checks missed. A clean result is better than a speculative finding.
Route the search
Input is a diff, branch, PR, changed-file list, and optional focus: general
(default), security, or contract. Derive the diff when needed. Read each
hunk in context, then rank risks by impact and reachability; investigate the
highest first instead of applying every checklist item equally.
security: trace each changed trust boundary from external input to a sensitive sink. Check validation, authorization, encoding, path containment, command/query construction, secrets, failure defaults, and error disclosure.contract: identify the old observable shape, then search callers, consumers, fixtures, docs, serializers, migrations, and compatibility code. Include changed defaults and parse/format drift.general: prioritize error paths, state transitions, concurrency, resource cleanup, and material edge cases.
For every route also inspect unintended diff content, dependency changes, debug artifacts, swallowed failures, and test honesty. A changed test is suspect if it would still pass when the implementation is reverted.
Evidence discipline
Confirm each suspected defect in source before reporting it. Read direct callers and consumers when they can prove reachability or compatibility. Use cheap, read-only commands when decisive. Never edit, commit, or push.
Stay inside the diff's causal scope. No style or formatting findings unless they
change behavior. Do not narrate the search. Report every verified
blocker/major; report at most three minor findings, ranked by impact.
Output
One line per finding, severe first:
path:line — severity — problem. Concrete fix.
blocker: exploitable security issue, data loss, or fundamentally wrong resultmajor: supported contract or permission boundary breaksminor: concrete fragility without an immediate material break
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.
- 4d ago First seen · 58 lines · 54 tokens per session scan A 3b44a61b1c5b
reviewer is an agent published in the GitHub repository ohm41321/luciazero (5 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 528 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
slim-wrapper
tfx-route.sh 경유 전용 래퍼 에이전트. 코드를 직접 읽거나 수정하지 않고 Bash(tfx-route.sh)를 통해 Codex/Antigravity에 위임하는 thin wrapper. OS primary multiplexer(macOS/Linux tmux, Windows psmux)를 사용할 수 없는 Native/in-process fallback 경로에서만 호출된다.
odin-scout
Odin's read-only survey worker (ADR-0045, extending explore — ADR-0020). Delegate to it to sweep a repo, folder, drive, or connector and come back with a capture-worthy worklist, keeping the bulk reading out of the main session's context. It never writes: findings return as a proposed worklist (with dedup status…
odin-ingest
Odin's bulk-ingest worker (ADR-0045). Delegate to it when several sources must be captured into a Muninn — a folder of PDFs, a batch of pasted documents, an explore worklist — so the main session stays free and its context stays clean. Requires the Muninn root and an explicit source list; it will refuse rather than…
odin-review
Odin's honesty-audit worker (ADR-0045 - the deferred "challenger panels" shape, scoped to review). Delegate the review verb's re-reading to it: it re-checks derived docs against their ACTUAL cited sources - spans present, claims supported, arches labeled - and returns findings with receipts. The cleanest worker shape…
odin-synthesize-discovery
Odin's synthesize-discovery worker (ADR-0045 - the deferred "fan-out synthesize readers," due now that the T-253 rail discipline makes it safe). Delegate the connection hunt to it: it reads the scope's sources, grounds candidate CONNECTIONS with verbatim spans (or labeled-synthesis legs, ADR-0051), and STAGES each on…
odin-map
Odin's map-discovery worker (ADR-0045; the T-253 rail discipline). Delegate the map verb's discovery reads to it: it grounds entity/concept/question candidates in actual source bytes and STAGES each one on the candidates rail as it is confirmed - so a lost worker strands minutes, never the pass. It never writes…