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 OutlineDriven/outline-driven-development --skill fresh-reader-reviewgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/fresh-reader-review)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/fresh-reader-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/fresh-reader-review/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/outlinedriven/outline-driven-development/fresh-reader-review"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/fresh-reader-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01001 |
| Opus 5 | $0.00033 | $0.00500 |
| Sonnet 5 | $0.00013 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
fresh-reader-review 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fresh reader review
Can a new reader understand the artifact without the context that produced it?
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks 'does this make sense to someone new' or 'cold-read this', or a README, document, skill, or PR description is about to ship. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | One or more isolated clean-room sub-sessions are dispatched depending on artifact stakes and size; the verdict and ordered fixes return in chat and the artifact is never edited. |
| Done | Blind sub-sessions, each reading only the inline artifact with no surrounding context, return a standalone verdict and severity-ordered fixes. |
Inputs
- Artifact (required): The file, document, or text to cold-read. Supplied inline as content, not as a repo path.
- Intent note (required): A one-line private note on what the artifact is meant to be and who it is for. The reviewer never sees this.
Procedure
- Pin scope and private intent. Identify the artifact in focus. Privately note in one line what it is meant to be and who it is for; the reviewer never sees this. Done when: the artifact is identified and the intent is privately noted.
- Segment the artifact if oversized. If the artifact exceeds what one sub-session can hold in context, split it into independent segments at natural boundaries (sections, chapters, files). Each segment gets its own blind read in step 3. Done when: the artifact is either confirmed as a single read or split into segments with boundaries marked.
- Dispatch the required number of blind sub-sessions. Each sub-session receives the artifact (or one segment) inline, not a repo path. Instruct every sub-session: (a) do not open the project's README, docs, or neighbors; (b) read only what is provided inline; (c) diagnose, do not fix. The number of sub-sessions is:
- One for a standard artifact with normal visibility.
- Multiple independent for a high-visibility artifact, irreversible publish, or safety-critical content. Use at least three; each gets the full artifact independently.
- One per segment for an oversized artifact that was split in step 2. Each sub-session reads only its segment. Done when: the required sub-sessions are dispatched with the artifact inline and isolation instructions.
- Collect blind understanding. Ask each sub-session to report what it takes the artifact to be, what is unclear or assumed but unstated, and what it had to guess before it could act. Done when: every sub-session reports its understanding, unclear points, and guesses.
- Compare blind understanding against intent. For each sub-session, compare its blind understanding against the intent noted in step 1. Every mismatch is a defect in the artifact. Done when: every mismatch is identified as a defect.
- Merge, deduplicate, and order defects. When multiple sub-sessions ran, merge their defect lists, deduplicate overlaps, and order by how badly each blocks a fresh reader. A defect reported by multiple independent sub-sessions ranks higher than one reported by a single sub-session. Done when: defects are ordered by severity with concrete fixes, or the verdict 'stands on its own' is returned with an empty fix list.
What ships with it
1 file 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.
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.
- 5d ago First seen · 50 lines · 66 tokens per session scan A b3a26a27e711
fresh-reader-review is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,001 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
create-pull-request
Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
gate-and-merge
Use when landing a queue of open PRs: gate each PR, sweep its review feedback to root cause, then merge, repair, hold, or close it. Human-only.
doubt-driven
Use when a non-trivial decision sits under uncertainty and correctness matters more than speed. Not for patch review: use review. Not for plan attacks: use load-bearing-assumption-test.
pr-review-canvas-html
Use when asked to render a GitHub PR as a standalone review HTML page. Fetches PR data via gh API, renders diffs with move detection, and serves the artifact on a local port. Not for Cursor Canvas output — use pr-review-canvas.
review
Use when asked to review a pull request, examine code changes, find bugs, or audit a branch. Standard mode produces a severity-graded validated-findings report with concrete fixes; depth mode fans out parallel bug/security and quality reviewers and synthesizes a unified verdict. Not for an iterative review-and-fix…