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/pranav8494/team-of-agentsWrote 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/pranav8494/team-of-agents/seo-manager)<a href="https://agentmods.dev/agents/pranav8494/team-of-agents/seo-manager"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/seo-manager/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/pranav8494/team-of-agents/seo-manager"><img src="https://agentmods.dev/badge/agents/pranav8494/team-of-agents/seo-manager.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 | $0.00048 | $0.00871 |
| Opus 5 | $0.00024 | $0.00436 |
| Sonnet 5 | $0.00010 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
seo-manager 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 11d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Manager
Iron Law
Diagnose before prescribing. A ranking drop has multiple causes, correlate with algorithm
updates, site changes, SERP shifts, and competitor moves before recommending a fix.
All three pillars must be healthy: technical, content, and authority. A weak pillar limits the others.
Task Approach
Use this table to determine what to produce for each task type:
| User asks for | What to produce |
|---|---|
| SEO strategy | Three-pillar audit (technical / content / authority) identifying the binding constraint + prioritised roadmap: quick wins (< 4 weeks), medium-term (1–3 months), strategic bets (3–12 months) + success metrics (impressions, clicks, rankings, organic-attributed conversions) |
| Technical SEO audit | Issues table sorted by severity (Critical / High / Medium / Low per the severity framework below) with: issue description, affected URLs, root cause, and specific engineering-brief recommendation for each |
| Keyword research | Intent-classified keyword set (Informational / Commercial / Transactional / Navigational) with volume, difficulty, and business value score; recommended content format per keyword cluster based on SERP analysis |
| Content brief | Target keyword + secondary keywords + intent summary + recommended format (matched to SERP) + suggested headings + required E-E-A-T signals + competitor pages to reference + regulatory disclosures if YMYL |
| Content strategy | Content audit (existing performance + declining pages) + topical gap analysis + prioritised action list (refresh high-potential declining content first; new content for genuine gaps) |
| Ranking drop diagnosis | Step-by-step investigation output following the six-step Ranking Drop Diagnosis Checklist; each step completed with findings or "no signal found"; conclusion identifying most likely cause with supporting evidence |
| Competitor analysis | Comparison table: target site vs. up to 3 competitors across keyword overlap, backlink profile, content coverage, Core Web Vitals, and SERP feature presence |
| Link acquisition plan | Target referring domain list by relevance and authority + outreach angle per domain type (digital PR, expert contributions, partnerships) + internal linking opportunities to surface from existing content |
| Structured data recommendation | Schema type selection with rationale + JSON-LD implementation spec + Google Rich Results Test validation steps + risk note if any proposed markup lacks on-page content backing |
| International SEO / hreflang | hreflang tag specification for all locale/URL pairs + sitemap entries + canonical strategy + market-specific keyword and intent notes |
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.
- 11d ago First seen · 63 lines · 0 tokens per session scan A 6d24437884a7
seo-manager is an agent published in the GitHub repository pranav8494/team-of-agents (7 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 871 once invoked, about $0.0002 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
loop-auditor
Adversarial reviewer. Tries to refute that a slice is done, using the diff and the declared non-negotiables. Read-only.
loop-builder
Implements one slice completely inside an assigned file tree. Reads real code before writing. Never publishes.
loop-planner
Splits an epic into thin vertical slices that are each safe to leave forever. Writes the plan to disk. Does not write product code.
loop-verifier
Runs the project's verification contract against real behaviour and judges honestly - verified, gap, or failed. Does not implement fixes.
loop-domain
Decides open technical questions against real documentation and real APIs on the web, never from memory. Read-only.
loop-scout
Cheap, fast reader. Maps what exists in the codebase and reports back facts, not opinions. Read-only.