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 OC-NeuralSense/reader-first-writing-skills/plugin install reader-first-writingWrote 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/oc-neuralsense/reader-first-writing-skills/review-document)<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/review-document"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/review-document/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/oc-neuralsense/reader-first-writing-skills/review-document"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/review-document.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 | $0.00191 | $0.02624 |
| Opus 5 | $0.00096 | $0.01312 |
| Sonnet 5 | $0.00038 | $0.00525 |
| Haiku 4.5 | $0.00019 | $0.00262 |
Grade A, and why
review-document 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 12d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-document
Purpose
Assess a complete or near-final document against reader-facing goals, applying the one quality lens its genre calls for, and (at audit depth) decide whether it may ship. This is an evaluative skill. It locates test-cited defects and renders a verdict; it does not apply fixes and never edits the user's text. Production and evaluation are kept separate on purpose: the party that wrote the passage is the wrong instrument to certify it.
When to use
- A document is near final and the writer wants it judged against its reader's needs.
- The writer asks whether it is ready to ship (audit gate).
When NOT to use (routing non-triggers)
- The writer wants a fast surface pass, not a graded review -> diagnose-draft (quick).
- The writer wants the full parallel multi-perspective run -> deep-review workflow.
- Two versions need comparing -> compare-versions.
Inputs
document(required)reader-framecontract (required)genre(required: ASK if absent; never inferred)communicative_aim(reveal | act)preservation_intent(strict | standard | loose)
Genre lenses (one lens per locked genre)
- business_analytical: answer-first placement; a real recommendation, not a topic label; support that genuinely establishes it; alternatives argued on the merits, not by demolishing straw versions; a calibrated action-seeking close. A policy memo is handled here as a sub-case: same answer-first discipline, reasoning-first only when the verdict will surprise.
- academic: inferential soundness (every step follows); evidence fits the claim; the treatment is complete for the question posed; counter-positions set up in their strongest form and engaged fairly; no overclaim: hedges and scope limits are load-bearing; a presentational, non-emoting close.
- general_explanatory: reader comprehension of an explanation that makes no recommendation; concepts pitched to the assumed prior knowledge; given-before-new progression; concrete or worked material where it aids grasp; no unexplained jargon; the explanation complete for the reader's standing question; a presentational, non-emoting close.
- technical_documentation: step completeness and non-overlap; preserved precision (no term silently narrowed or widened); picturability of each step; navigation apparatus (headings, ordering, signposting) a scanning reader can trust.
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.
- 12d ago First seen · 188 lines · 191 tokens per session scan A 04a6610cd076
review-document is a skill published in the GitHub repository OC-NeuralSense/reader-first-writing-skills (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 191 tokens to every session and 2,624 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
provider-integration
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…
update-lid
Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…
recursive-decomposition
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered…
arrow-maintenance
Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…
map-codebase
Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…