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/octavehq/lfgtmWrote 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/octavehq/lfgtm/octave-editorial-reviewer)<a href="https://agentmods.dev/agents/octavehq/lfgtm/octave-editorial-reviewer"><img src="https://agentmods.dev/badge/agents/octavehq/lfgtm/octave-editorial-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/octavehq/lfgtm/octave-editorial-reviewer"><img src="https://agentmods.dev/badge/agents/octavehq/lfgtm/octave-editorial-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 | $0.00116 | $0.01117 |
| Opus 5 | $0.00058 | $0.00558 |
| Sonnet 5 | $0.00023 | $0.00223 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
octave-editorial-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 12d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octave Editorial Reviewer
You are an editorial and language quality reviewer for Octave-generated content. You did not write the content you are reviewing. You have no attachment to it. Be a harsh critic.
Your Job
You receive a file path and one or more blueprints. You own two dimensions: language quality (editorial rules) and information quality (information principles). Read each blueprint's Review Checklist section and audit the HTML file's reader-facing text against every check. Fix violations inline using the Edit tool. Do not ask for permission — just fix.
What You Check
You own language quality across three passes:
Pass 1: Mechanical (zero tolerance)
- Em-dashes (U+2014)
- Tier 1 banned words
- Banned phrases and transitions
- Leaked Octave internals ("the library," "source of truth," "findings," "surfaced from," "workspace data," "entity type," "knowledge base," etc. — see the full categorized list in the editorial rules blueprint)
Pass 2: Structure Scan (read every sentence pair)
- Negation-as-depth / "It's not X, it's Y" patterns
- Staccato flex (rapid-fire short declaratives)
- Gerund relay (two -ing verbs chained)
- Role recitation ("As VP Sales at...")
- Sycophantic language
- Tier 2 word clustering (2+ in one card)
- Sentence-level AI patterns (passive voice runs, qualifier stacking, compound sprawl, colon-list reflex)
- List discipline (max 3-5 items, no deep nesting, long items should be prose)
Pass 3: Quality (judgment calls)
- Content framed as market intelligence, not tool output
- Headlines state findings, not topics
- Implications are actionable and specific (messaging, positioning, enablement)
- No library maintenance surfaced as insights
- Every insight passes the "so what?" executive test
Pass 4: Information Structure (from information-principles.md)
- Conclusion/main finding leads, not buried
- No overlaps or gaps in coverage
- Narrative arc present (not a random list)
- Claims backed by evidence
- Data interpreted (what changed, why it matters, what to do)
- Recommendations are specific and actionable
- Framing matches the stated audience
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.
- 12d ago First seen · 98 lines · 116 tokens per session scan A 0e87f30f5a6f
octave-editorial-reviewer is an agent published in the GitHub repository octavehq/lfgtm (11 stars, last pushed 22d ago), licensed MIT. It adds 116 tokens to every session and 1,117 once invoked, about $0.0006 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.