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 skills add manishiitg/coding-agent-loop --skill website-growth-loopgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/skills/manishiitg/coding-agent-loop/website-growth-loop)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/website-growth-loop"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/website-growth-loop/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/skills/manishiitg/coding-agent-loop/website-growth-loop"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/website-growth-loop.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 | $0.00035 | $0.00794 |
| Opus 5.5 | $0.00014 | $0.00318 |
| Sonnet 5.5 | $0.00007 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
website-growth-loop 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 20d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website Growth Loop
Outcome
Coordinate Crews to find traffic opportunities, prepare improvements, and measure the owner's visitor goal.
When to use
Use for a new site seeking relevant visitors. Public pages and owner context support a first manual run. Add connected measurement later. Use a Crew schedule for one repeating specialist.
Discovery and user direction
Inspect the Automation, Crews, skills, access, and goals. Propose the team, handoffs, cost, and blockers; record owner decisions. Selection does not authorize creation or runs.
Track setup in SETUP.json. Verify checks, save references under evidence[id], and report blockers.
Required inputs
Resolve site, offer, audience, market, visitor action, crawl scope, owner, metric, baseline decision, and publication boundary. Search Console and analytics are optional initially; never invent history.
Plan and AgentWorks tools
Use Website Growth Starter and Search Opportunity Mapper as distinct required Crews. Reuse suitable Crews; technical SEO is optional. After owner review, use create_crew with stable idempotency keys for missing specialists. Bind internal triggers and attachments. Add blocking validation after each selected producer: strategist, search, content, page, publication, distribution, measurement. Test the route manually before proposing recurrence.
Knowledge and persistence
Save decisions, scope, metrics, Crew bindings, evidence, and windows. Track stable action IDs and states. Pass bounded artifacts. Read previous runs and decisions before repeating; report changes.
Validation and reporting
Verify two required Crew IDs, skills, access, exact artifact IDs, and a manual run. For optional routes, verify approved content and page claims, separate publication approval and receipt, live-page checks, channel delivery receipts, and comparable measurement counts. Prove invalid artifacts stop the next Crew. The dashboard shows action state, sources, baseline, denominators, run IDs, cost, and blockers.
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/approved-page-draft.json 1023 B
- examples/content-brief.json 1.3 KB
- examples/distribution-plan.json 876 B
- examples/growth-priority-brief.json 2.6 KB
- examples/invalid-content-brief.json 928 B
- examples/invalid-distribution-plan.json 739 B
- examples/invalid-page-draft.json 804 B
- examples/invalid-search-opportunity-list.json 840 B
- examples/invalid-shipped-change.json 906 B
- examples/invalid-traffic-readout.json 1.4 KB
- examples/reviewable-page-draft.json 1022 B
- examples/search-opportunity-list.json 1.8 KB
- examples/shipped-change.json 1011 B
- examples/traffic-readout.json 1.4 KB
- examples/website-growth-run.json 1.3 KB
- playbook.json 6.4 KB
- references/action-and-measurement.md 4.9 KB
- references/team-and-handoffs.md 11 KB
- scripts/test_validate_handoff.py 6.8 KB runs code
- scripts/validate_growth_artifact.py 28 KB runs code
- SETUP.json 3.2 KB
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.
- 20d ago First seen · 56 lines · 35 tokens per session scan A bbb4a08eab09
website-growth-loop is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 35 tokens to every session and 794 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 2026-09-27.
Other skills, from other repositories
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.