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 VPDPersonal/Aspid.FastTools --skill docs-reviewgit clone --depth 1 https://github.com/VPDPersonal/Aspid.FastToolsWrote 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/vpdpersonal/aspid.fasttools/docs-review)<a href="https://agentmods.dev/skills/vpdpersonal/aspid.fasttools/docs-review"><img src="https://agentmods.dev/badge/skills/vpdpersonal/aspid.fasttools/docs-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/vpdpersonal/aspid.fasttools/docs-review"><img src="https://agentmods.dev/badge/skills/vpdpersonal/aspid.fasttools/docs-review.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 | $0.00079 | $0.01006 |
| Opus 5.5 | $0.00032 | $0.00402 |
| Sonnet 5.5 | $0.00016 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
docs-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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docs page review
A review checks one page and proposes changes. The first pass never edits anything.
Scope
- Review feature pages (
Website/docs/NN-*.md) and sample pages (Website/tutorials/<Sample>/README.md). - Never review the Introduction (
Website/docs/README.md). It is the reference for all other pages.
Steps
- Load the
docs-siteskill. Its rules are the checklist. - Read the English page and its Russian twin in
Website/i18n/ru/. - Run
Website/scripts/serve-all.sh. Open the Russian page of this checkout in the built-in browser. - Look at every section on screen.
- Extract frames from each GIF. Look for empty UI, encoder residue and cursor jumps.
- Check the page against the source. If the
docs-verifieragent exists, start it in the background and give it the page pair, the source folders and the claims to check. If not, follow "Check without the agent". - Compare the page with the Introduction and ProfilerMarkers: lead, quick start, density and visuals.
- Send the review in the format below. Do not edit yet.
- When the user answers, apply what they accepted to both languages. Rebuild and check the page.
- Then the user goes section by section. A stated decision is a "yes": edit at once and rebuild.
- If a remark is ambiguous, state your reading in one line and apply it. Ask only on «что думаешь».
- A user remark can apply to other pages too, and no rule may cover it yet. Then propose a rule in one line.
- Add the rule to
docs-siteonly after the user's yes. A remark about one page only stays a page edit.
Check without the agent
The docs-verifier agent is not in this repository. Without it, do the check yourself. The check changes no files.
- List the claims on the page: type, member and attribute names, signatures, namespaces,
usinglines, sample paths, menu paths, default values, versions and install URLs. - Find the names in one call:
grep -rnE 'Name1|Name2'overAspid.FastTools/Packages/tech.aspid.fasttools. - Read the declarations, not the usages. A code sample must compile: check every call and every argument.
- For a feature list, grep the public types and compare them with the list on the page.
- Compare the English and Russian pages section by section.
- Note each mismatch as
<page>:<line> — <claim> → <what the code says> (<file>:<line>). Use the notes in the review (step 8).
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.
- 4d ago Changed · +13 lines 117f92b9855a
- 11d ago First seen · 52 lines · 79 tokens per session scan A 890472a56573
docs-review is a skill published in the GitHub repository VPDPersonal/Aspid.FastTools (24 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 1,006 once invoked, about $0.0003 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 2026-10-05.
Other skills, from other repositories
test-designing-guide
Provides test design methodology for Unity projects. Use this skill whenever designing test cases from requirements or specifications, including selecting test techniques, deriving test cases, and formatting them. Even for small features, load this skill to ensure test design rigor.
fix-bug
Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…
refine-tests
Reviews existing test code for conformance to the test-designing-guide and test-writing-guide, then applies the refinements. Use this skill when the user wants to review or refine existing test code so it follows the project's test design and writing conventions. Typically invoked as /refine-tests .
test-writing-guide
Provides guidelines for writing test code for Unity projects. Make sure to use this skill whenever writing, creating, editing, or modifying test code files (files under Tests/). This includes implementing new tests, fixing test failures, adding test cases, or any task that results in test code changes. Even for small…
plan-feature
Orchestrates the test-first implementation planning workflow for feature implementation and spec changes. Use this skill whenever plan mode is active and the task involves implementing or adding a new feature, or changing an existing specification. Even if the user only says "plan this" or "how should we implement…
edit-scene
Creates and modifies Unity scene and prefab files. Use this skill whenever creating, editing, or modifying .unity scene files or .prefab prefab files. This includes adding GameObjects, building uGUI hierarchies, wiring up components, and any task that results in changes to .unity or .prefab files.