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 growth-experimentation-follow-throughgit 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/growth-experimentation-follow-through)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/growth-experimentation-follow-through"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/growth-experimentation-follow-through/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/growth-experimentation-follow-through"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/growth-experimentation-follow-through.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 | $0.00024 | $0.00835 |
| Opus 5.5 | $0.00010 | $0.00334 |
| Sonnet 5.5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
growth-experimentation-follow-through 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Growth Experimentation and Follow-Through
Outcome
Experiment Run Coordinator verifies a frozen, approved plan and provider launch. Growth Outcome Analyst measures pre-registered primary and guardrail metrics after the full window. A plan, ticket or early difference is not a live experiment or win.
When to use
Use after a sourced growth question has a plan from Campaign Signal, Funnel and Conversion, Activation and Retention, SEO, AI Visibility, or an equivalent source. Freeze and approve the plan before launch. This Playbook tracks execution and readout; it grants no change authority.
Discovery and user direction
Builder inspects plan revision, decision, Crews, provider, allocation, sources, owners, window and sample rule. It proposes run and outcome Crews in chat. Selection creates no Crew, ticket, flag, message or schedule.
Required inputs
Record experiment/product/tenant IDs, frozen plan artifact and revision, eligible account rule, control/treatment IDs and allocation, primary and guardrail definitions, minimum sample, readout window, stop rule, approval policy, rollout and rollback owners, provider state and source access.
Plan and AgentWorks tools
- Bind Crew IDs and Workflow steps. Save a sourced
frozen-experiment-plan/v1snapshot. Run Coordinator savesexperiment-execution-record/v1withpending_approvalorlaunchedstate. A launch needs exact plan approval, provider launch receipt and exposure source. Runpython3 scripts/validate_handoff.py execution <plan.json> <record.json>as a blocking step. - A pending record stops outcome claims. For provider-confirmed launch, pass the validated artifact by checked alias. Outcome Analyst saves
experiment-outcome-readout/v1aspending_window,inconclusiveormeasured. Runpython3 scripts/validate_handoff.py readout <plan.json> <record.json> <readout.json>before reporting. - The owner reviews measured or inconclusive evidence. Shipping, rollback, budget, CRM, contact and notification actions use separately approved routes and provider receipts.
What ships with it
15 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/experiment-backlog.json 858 B
- examples/experiment-execution-record.json 2.0 KB
- examples/experiment-inconclusive-readout.json 1.9 KB
- examples/experiment-measured-readout.json 1.8 KB
- examples/experiment-pending-approval.json 1.4 KB
- examples/experiment-pending-window.json 887 B
- examples/frozen-experiment-plan.json 1.5 KB
- examples/invalid-experiment-execution.json 1.8 KB
- examples/invalid-experiment-readout.json 1.9 KB
- playbook.json 5.4 KB
- references/experimentation-workflow.md 2.3 KB
- references/team-and-handoffs.md 3.3 KB
- scripts/test_validate_handoff.py 4.5 KB runs code
- scripts/validate_handoff.py 12 KB runs code
- SETUP.json 3.1 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 Changed · +1 lines · -21 tokens per session 94364cfa3e96
- 1mo ago First seen · 51 lines · 45 tokens per session scan A 36ec736af113
growth-experimentation-follow-through is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 24 tokens to every session and 835 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 2026-09-15.
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.