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 released-feature-to-adoption-decisiongit 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/released-feature-to-adoption-decision)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/released-feature-to-adoption-decision"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/released-feature-to-adoption-decision/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/released-feature-to-adoption-decision"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/released-feature-to-adoption-decision.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 | $0.00023 | $0.00755 |
| Opus 5.5 | $0.00009 | $0.00302 |
| Sonnet 5.5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
released-feature-to-adoption-decision 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Released Feature to Adoption Decision
Outcome
Show how many eligible accounts saw and used one released feature under a frozen rule, then prepare a product owner decision. The observation may be a baseline, comparable repeat, or not evaluable. Usage does not prove causality.
When to use
Use after release or flag exposure when Product wants to investigate, iterate, keep or stop a feature. New Customer to First Value measures one customer's agreed outcome; this route measures an eligible segment. An unreleased flag does not qualify.
Discovery and user direction
Builder inspects Product Adoption Analyst and Product Feedback Coordinator skills, release and flag source, eligible segment, event identity, coverage and owner criteria. Propose reuse of compatible Crews, validated steps and a manual case before configuration. Selecting the Playbook starts no event, issue, feature-flag change or schedule.
Required inputs
Bind tenant, product, feature, release/build, flag revision, segment, equal-window policy, distinct-account join, eligibility, exposure and use predicates, predeclared target, minimum exposed sample, source coverage, current issue source and product owner. Missing instrumentation yields not_evaluable and an explicit next measurement step.
Plan and AgentWorks tools
Workflow steps: Product Adoption Analyst reads the authorized release, flag and analytics exports, deduplicates accounts, and emits feature-adoption-observation/v1. Run the packaged validator as a blocking step. Product Feedback Coordinator receives only the validated artifact, re-reads current release and issue state, and emits feature-adoption-decision/v1; validate the exact pair. Ask the product owner to review the recommendation and gaps. Any issue write, flag change, customer message or experiment launch is a separate approved action with a provider receipt.
Knowledge and persistence
Keep release/build, flag and rule versions, windows, eligibility and event-source revisions, observation IDs, owner decisions and case keys. On repeat, compare equal windows under the same definitions and preserve corrected counts. A changed flag or instrumentation rule starts a new baseline.
What ships with it
10 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/feature-adoption-comparable.json 1.8 KB
- examples/feature-adoption-decision.json 1.3 KB
- examples/feature-adoption-not-evaluable.json 1.3 KB
- examples/feature-adoption-observation.json 1.3 KB
- examples/invalid-feature-adoption-decision.json 1.4 KB
- playbook.json 4.4 KB
- references/team-and-handoffs.md 2.3 KB
- scripts/test_validate_handoff.py 4.2 KB runs code
- scripts/validate_handoff.py 9.9 KB runs code
- SETUP.json 2.6 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 · 49 lines · 23 tokens per session scan A a041798f1e56
released-feature-to-adoption-decision is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 755 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.
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.
craft-studio
Router for the ArtCraft craft apps (PhotoCraft, VectorCraft, FilmCraft, LightCraft, PdfCraft, EffectCraft, DesignCraft, FigCraft, WordCraft, SoundCraft, DeckCraft, CADCraft, GridCraft) driven headless via pi-craft. Use to choose which app fits a job and run the discover-execute-save-verify loop - "which craft app…