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 campaign-signal-to-reviewed-experimentgit 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/campaign-signal-to-reviewed-experiment)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/campaign-signal-to-reviewed-experiment"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/campaign-signal-to-reviewed-experiment/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/campaign-signal-to-reviewed-experiment"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/campaign-signal-to-reviewed-experiment.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 | $0.00025 | $0.00664 |
| Opus 5.5 | $0.00010 | $0.00266 |
| Sonnet 5.5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
campaign-signal-to-reviewed-experiment 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign Signal to Reviewed Experiment
Outcome
Explain one campaign change with comparable spend, click and qualified-event evidence, then propose one testable experiment. A performance correlation, approved plan, launched variant and observed result are separate states.
When to use
Use when a B2B team wants to move from a campaign signal to a reviewed next test. One Crew may hold both capabilities for the same owner and access; separate Crews when measurement and change authority differ. Competitive context is optional.
Discovery and user direction
Inspect existing Marketing Crews, account/campaign/offer IDs, current and baseline sources, conversion definition, attribution and lag, eligible audience, owner and experiment destination. Ask only for missing choices. Show the concrete proposal before Builder applies it.
Required inputs
Bind tenant, campaign platform account, campaign, offer, market, currency, periods, time zone, click and qualified-event definitions, source revisions, baseline, coverage, owner, primary metric, guardrail and sample/stop policy. Missing data remains explicit.
Plan and AgentWorks tools
Reuse Campaign Performance Analyst and Growth Experiment Planner; add Competitor Intelligence Analyst only for a bounded, dated source question. Performance writes campaign-performance-brief/v1. Run the bundled validator before Experiment consumes it. Optional Competitor writes competitor-context/v1 and is validated separately. Experiment writes growth-experiment-plan/v1; validate its join and decision rule. Insert explicit validator steps in the Workflow. Publishing a variant, changing spend or sending a message requires a separate exact approval and provider receipt.
Knowledge and persistence
Save campaign/account/offer, period, metric definition, denominator, source, competitor product, plan, experiment, approval, provider and run IDs. On later periods, preserve the comparison policy, account for attribution lag and avoid duplicate alerts or launches.
What ships with it
9 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/campaign-performance-brief.json 1.4 KB
- examples/competitor-context.json 724 B
- examples/growth-experiment-plan.json 1.4 KB
- examples/invalid-growth-experiment-plan.json 1.2 KB
- playbook.json 5.2 KB
- references/team-and-handoffs.md 2.7 KB
- scripts/test_validate_handoff.py 3.6 KB runs code
- scripts/validate_handoff.py 9.1 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 First seen · 48 lines · 25 tokens per session scan A 60a74d069b1d
campaign-signal-to-reviewed-experiment is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 25 tokens to every session and 664 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.