assessing-quality

assessing-quality is a skill for Claude Code from isvlasov/rageatc-oss. It costs 43 tokens per session (1,529 once invoked), scanned A, original, MIT.

A review process for non-code materials such as skills, agents, workflows, documentation and written content. It records what meets the standard, prioritises issues and gives next steps.

In plain words
What is it for?
Use it to assess quality against a brief or defined standards before releasing or revising an artefact.
Why use it?
It turns a general critique into specific improvements that can be acted on and checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rageatc-core-oss plugin — 24 skills, 6 agents shipped together

Good fit Use it to assess quality against a brief or defined standards before releasing or revising an artefact.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/isvlasov/rageatc-oss/assessing-quality
Install

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.

Any agent
npx skills add isvlasov/rageatc-oss --skill assessing-quality
Clone the repo
git clone --depth 1 https://github.com/isvlasov/rageatc-oss

Made for: Claude Code.

Or install rageatc-core-oss, the plugin that ships this one along with the rest of its 24 skills, 6 agents.

Wrote 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.

agentmods badge for assessing-quality

README.md
[![agentmods](https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/assessing-quality/github.svg)](https://agentmods.dev/skills/isvlasov/rageatc-oss/assessing-quality)
Your own site
<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/assessing-quality"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/assessing-quality/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.

agentmods 80×15 button for assessing-quality

Your own site · 80×15
<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/assessing-quality"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/assessing-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,529 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01529
Opus 5 $0.00022 $0.00764
Sonnet 5 $0.00009 $0.00306
Haiku 4.5 $0.00004 $0.00153

Measured 10d ago against content hash d118bc721d83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

assessing-quality 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.

plugins/rageatc-core-oss/skills/assessing-quality/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assessing Quality

Produce reviews that guide improvement, not just identify problems: validate what meets standards, categorise issues by priority with root causes, and give specific "where to next" guidance for every issue.

Output format

Save to work/<task-id>/review_v[N].md:

# Review: [Artefact Name] v[N]

**Reviewed:** YYYY-MM-DD
**Artefact Type:** [Skill/Agent/Workflow/Documentation]
**Applicable Standards:** [List]

## Summary
[Overall assessment in 2-3 sentences]

## What Meets Standards
[Validation of what works well — builds shared understanding]

## Priority Issues

### High Priority
**[Issue Title]**
- Symptom: [specific observation with location]
- Root cause: [underlying reason]
- Impact: [effect on purpose, audience, or standards]
- Where to next: [specific, actionable fix guidance]

### Medium Priority
[Same structure]

### Low Priority / Recommendations
[Suggestions with rationale]

## Assessment Against Standards
[Checklist from brief.md: [x] met, [~] partially met (specify gap), [ ] not met]

## Next Steps
[Prioritised by impact]

Workflow

Stage 1 — Prepare

  1. Read the artefact fully. Note initial impressions; don't judge yet.
  2. Read work/<task-id>/brief.md and extract its requirements checklist (the "Requirements Extracted from Standards" section). If that section is missing, identify applicable standards from the brief's context and extract requirements from those skills directly.
  3. Note the artefact type and whether this is a v1 review or a v2+ iteration review.

Stage 2 — Assess

Evaluate against six core dimensions, documenting specific observations with locations:

  • Completeness — required components present; checklist items addressed; no placeholders remain
  • Clarity — understandable to the intended audience; terms defined at first use; examples for abstract concepts
  • Correctness — factually accurate; internally consistent; references valid
  • Consistency — one term per concept throughout; formatting patterns repeated; aligned with cited standards
  • Fitness for purpose — the brief's target audience can apply it successfully; stated goals met; scope neither too narrow nor too broad
  • Signal-to-noise — every passage changes something for the intended reader (their understanding, decision, or action); flag text that doesn't: filler, internal repetition, ceremony, explaining what the reader already knows. Noise is a quality defect, not a style preference — it buries the signal and costs the reader attention. Detail needed only conditionally belongs in references or appendices, not the body. Noise repeating across the artefact is systemic (Stage 4)

Read the full file on GitHub · 132 lines

Changes

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.

  1. 10d ago First seen · 132 lines · 43 tokens per session scan A d118bc721d83

Subscribe to this mod's changes

assessing-quality is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,529 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 2026-08-31.