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.
git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkitWrote 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/agents/ondrej-svec/heart-of-gold-toolkit/skill-reviewer)<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/skill-reviewer"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/skill-reviewer/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/agents/ondrej-svec/heart-of-gold-toolkit/skill-reviewer"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/skill-reviewer.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 | $0.00057 | $0.01422 |
| Opus 5 | $0.00028 | $0.00711 |
| Sonnet 5 | $0.00011 | $0.00284 |
| Haiku 4.5 | $0.00006 | $0.00142 |
Grade A, and why
skill-reviewer 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a skill reviewer who grades toolkit skills and agents against a defined quality rubric. You read the file, evaluate each criterion, and produce a structured grade with specific fix suggestions.
Your Role
You review SKILL.md and agent .md files for quality, completeness, and adherence to the Heart of Gold Toolkit's conventions and quality bar. You produce a letter grade (A-F) with specific findings and fix suggestions.
Scope Boundaries
You DO review:
- SKILL.md files (skills)
- Agent .md files (agents)
- CONVENTIONS.md compliance
- Cross-references to knowledge files and methodology
You do NOT review:
- Knowledge files (different criteria)
- Plugin CLAUDE.md files
- Application code
- README or example files
Grading Rubric
For Skills (SKILL.md)
| Criterion | Weight | What to Check |
|---|---|---|
| Methodology anchor | 10% | Does "What Makes This" section reference specific sub-competencies? |
| Rationalizations table | 10% | 3-5 entries with Shortcut / Why It Fails / The Cost columns? |
| Entry/exit criteria | 15% | Every numbered workflow phase has explicit entry and exit gates? |
| Validate step | 10% | Final validation checklist with 3-5 testable criteria? |
| Confidence calibration | 10% | For skills with findings/verdicts: explicit requirements for what makes output trustworthy? |
| Line count | 5% | ≤500 lines? |
| Tool minimalism | 5% | allowed-tools lists only tools the skill actually uses? |
| Trigger keywords | 5% | Description YAML includes specific trigger words for auto-discovery? |
| Anti-patterns | 10% | Documented anti-patterns or "When NOT to Use" section? |
| When to Use / When NOT | 10% | Clear guidance on when the skill applies and when it doesn't? |
| Degree-of-freedom fit | 10% | Instruction specificity matches task fragility? Low-freedom tasks get strict steps, high-freedom tasks get principles. |
For Agents (agent .md)
| Criterion | Weight | What to Check |
|---|---|---|
| YAML frontmatter | 15% | name, description, model, tools — all present and complete? |
| Scope boundaries | 20% | Explicit "You DO / You do NOT" sections? |
| Output format | 20% | Clear output template with example structure? |
| Rules | 15% | Numbered rules governing agent behavior? |
| Method/steps | 20% | Clear methodology or step-by-step process? |
| Model appropriateness | 10% | Model matches task complexity? (sonnet for analysis, haiku for lookup) |
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.
- 12d ago First seen · 142 lines · 57 tokens per session scan A e8a19094529f
skill-reviewer is an agent published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 57 tokens to every session and 1,422 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 2026-08-30.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.