Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add alphabravo-oss/guild/plugin install websterWrote 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/alphabravo-oss/guild/reader-lens)<a href="https://agentmods.dev/skills/alphabravo-oss/guild/reader-lens"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/reader-lens.svg" alt="Measured on agentmods" 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 | $0.02296 |
| Opus 5 | $0.00024 | $0.01148 |
| Sonnet 5 | $0.00010 | $0.00459 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
reader-lens 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 yesterday.
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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reader lens
audience used to buy one thing: a reading grade. That is not enough, and the gap is visible in
the output. A page can describe a status enum in short words and pass at grade 9:
A deployment's status is the field everything else in the UI hangs off. This page is about how that field moves. It is also about the sub-phase field underneath it.
Nothing there is untrue, nothing is long-winded, and it is not documentation. It is a developer's model of the system handed to somebody who wanted to know whether their cluster was ready.
So the audience is a lens before it is a grade. It decides subject matter first and sentence length second.
The rule
A page may name only the things its reader can touch.
| Audience | May name | May not name |
|---|---|---|
user |
Screens, buttons, fields, menus, files they have, what the product gives back, what it says when something fails | Symbols, routes, environment variables, architecture |
operator |
All of the above, plus commands, flags, config files, environment variables, ports, logs | Symbols and architecture |
developer |
Anything in the system | nothing |
doctype.py check enforces this. On a page below developer it is a defect to name a symbol in
backticks, a request route, or a part of the architecture, and on a user page an environment
variable as well. A page that declares no reader is itself a defect: in the last full run of this
plugin before the rule existed, not one of 67 pages declared an audience, so the lens never fired.
Writing from the screen
The reliable move is mechanical. Before writing a user page, get the words the product prints
on itself. survey.py returns them under user_surface:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/survey.py . > .webster-survey.json
WEBSTER_SURVEY=.webster-survey.json \
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/doctype.py check docs
Save the survey and pass it. It is not an optional courtesy: it is the only oracle the lens
has that lives outside the thing being judged. With it, the product's own screen and button
names stop being reported as internal symbols, and an environment variable is one the code
actually reads. Without it, whether PIONEER_API_URL on a user page is a leak depends on
whether some other page in the same set happens to show it being assigned, which means adding a
page changes the verdict on a different page and deleting one makes a defect disappear. The
check says which oracle it used on every run.
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.
- yesterday First seen · 189 lines · 48 tokens per session scan A f2e62a955405
reader-lens is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 2,296 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…