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 isvlasov/rageatc-oss --skill assessing-qualitygit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/assessing-quality)<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.
<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>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 | $0.00043 | $0.01529 |
| Opus 5 | $0.00022 | $0.00764 |
| Sonnet 5 | $0.00009 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
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.
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
- Read the artefact fully. Note initial impressions; don't judge yet.
- Read
work/<task-id>/brief.mdand 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. - 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)
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 · 132 lines · 43 tokens per session scan A d118bc721d83
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.
Other skills, from other repositories
challenge
Use before a root-cause, done/verified claim, irreversible action, or 2nd-time fix reaches the owner (APEX or plain conversation); also fires at every eLicit/Verify gate. Not for code correctness (use sniper).
code-quality
Use when validating code quality after modifications -- SOLID compliance, DRY duplication, linter errors, architecture violations. Do NOT use for functional verification (run verification FIRST, then code-quality).
elicitation
Use when an expert agent self-reviews and self-corrects code after the Execute phase, before sniper validation (BMAD-METHOD elicitation techniques).
react-effects-audit
Use when auditing React or Next.js components for unnecessary or unsafe useEffect usage -- detects 9 anti-patterns from "You Might Not Need an Effect".
pr-summary
Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.
sniper-check
Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.