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/build-argument)<a href="https://agentmods.dev/skills/oc-neuralsense/reader-first-writing-skills/build-argument"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/build-argument/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/build-argument"><img src="https://agentmods.dev/badge/skills/oc-neuralsense/reader-first-writing-skills/build-argument.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 | $0.00183 | $0.01729 |
| Opus 5 | $0.00092 | $0.00864 |
| Sonnet 5 | $0.00037 | $0.00346 |
| Haiku 4.5 | $0.00018 | $0.00173 |
Grade A, and why
build-argument 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 10d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-argument
Purpose
Convert raw material into a validated logical skeleton: one governing question, one lead answer, and a summary-before-detail hierarchy of grouped, screened claims. This is a generative skill. Grouping and ordering are its subroutines, handled in one activation.
When to use
- A reader-frame exists and the material is unstructured or unordered.
- The writer wants an answer-first outline, a governing question, clusters, or an ordering: all served here.
When NOT to use (routing non-triggers)
- Only wants an existing structure's soundness checked -> test-argument.
- Wants continuous prose from an approved outline -> draft-prose.
- Wants apparatus density or the ending chosen -> shape-and-close.
Inputs
reader-framecontract (required: run frame-the-brief first if absent)notes_or_claims_or_topic(required)
Workflow
- Reduce to one governing question, scaled to the reader's gap.
- State the controlling idea as a one-line answer, separating subject from point.
- Inventory and screen claims for soundness and relevance; every input note is placed under a parent or moved to a labeled drop list; nothing vanishes silently.
- Assemble the hierarchy so each parent genuinely summarizes its children.
- Group (subroutine): one logical kind per group, non-overlapping, judged complete; each parent carries a substantive label, never a bare count/category.
- Order (subroutine): sequence each group by its formation logic (time, part-structure, or degree), reconciled with reader load.
- Place the answer. Answer-first by default; invert to reasoning-first only on an expected-disagreement trigger.
- Build the opening backward from the settled answer: context, tension, question, answer.
- Validate and emit the argument-blueprint.
Decision rules
- Exactly one governing question and one controlling idea, subject and point split.
- No orphan claims; every claim has a parent or is on the drop list.
- Empty toppers are banned regardless of stakes; MECE rigor scales with stakes.
- Ties between valid orderings break toward lower reader effort.
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.
- 10d ago First seen · 152 lines · 183 tokens per session scan A d80d949f1dc1
build-argument 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 183 tokens to every session and 1,729 once invoked, about $0.0009 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…
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…
review-pr
A pull-request review skill for evaluating proposed code changes and posting a quality verdict. A pull request is a request to merge changes into a shared codebase.