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 Terryc21/skill-reviewer --skill skill-reviewergit clone --depth 1 https://github.com/Terryc21/skill-reviewerWrote 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/terryc21/skill-reviewer/skill-reviewer)<a href="https://agentmods.dev/skills/terryc21/skill-reviewer/skill-reviewer"><img src="https://agentmods.dev/badge/skills/terryc21/skill-reviewer/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/skills/terryc21/skill-reviewer/skill-reviewer"><img src="https://agentmods.dev/badge/skills/terryc21/skill-reviewer/skill-reviewer.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 | $0.00071 | $0.02110 |
| Opus 5 | $0.00036 | $0.01055 |
| Sonnet 5 | $0.00014 | $0.00422 |
| Haiku 4.5 | $0.00007 | $0.00211 |
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 9d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-reviewer
Installed as a Claude Code plugin in v0.1. Invoke as
/skill-reviewer <subcommand>. The plugin registers/skill-revieweras a single skill activation; Claude parses the argument string as a subcommand. There is no per-subcommand autocomplete or native slash command for each row in the table below — they are subcommand strings the skill recognizes, not registered commands.
Candid, no-bullshit reviews of Claude Code skills. Honest about strengths and weaknesses both.
Why this skill exists
Skill authors get polite-by-default feedback. Reviewers want to be helpful, so they hedge: "consider adding tests," "you might think about discoverability." That kind of feedback ships skills with quiet flaws — silent test gaps, unparseable output formats, trigger phrases that never fire.
skill-reviewer was extracted from a real review session where a skill author wanted blunt critique with file:line citations and ranked actions. The pattern worked. This skill bottles it.
Three things distinguish a skill-reviewer report from generic feedback:
- File:line citations for every claim. No "this could be clearer" without saying where and why.
- Equal weight to strengths and weaknesses. Reviews that only list problems tell authors what to change but not what to preserve.
- Severity rubric with effort estimates. Quick wins are tagged so authors can pick low-cost-high-leverage fixes first.
Subcommand surface
| Subcommand | Purpose | Full spec |
|---|---|---|
/skill-reviewer review <path> |
Full review of one skill | reference/protocol.md |
/skill-reviewer review <path> --lens=<name> |
Focused review under a lens | reference/lenses.md |
/skill-reviewer review <path> --second-opinion |
Full review + reconciliation pass | reference/second-opinion.md |
/skill-reviewer summary <path> |
TL;DR + top 5 strengths + top 5 weaknesses only | reference/lenses.md (quick lens) |
/skill-reviewer lenses |
List available lenses with descriptions | reference/lenses.md |
/skill-reviewer detect <path> |
Classification only; print shape + recommended review depth | reference/detection.md |
/skill-reviewer --version |
Print version, install path, supported lens names | reference/output-format.md § --version output |
What ships with it
8 files 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.
- 9d ago First seen · 127 lines · 0 tokens per session scan A 63aeafdfaa8a
skill-reviewer is a skill published in the GitHub repository Terryc21/skill-reviewer (52 stars, last pushed 11d ago), licensed Apache-2.0. It adds 71 tokens to every session and 2,110 once invoked, about $0.0004 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 skills, from other repositories
uplevel
Establish, automate, and enforce a project's engineering process — the gate that runs before every commit, the checks that replace it with automation, the environment and deploy discipline that keeps production safe, and the irreversible operations that need explicit sign-off. Use when the user asks to "uplevel this…
ring:migrating-to-lib-observability
Migrating a Lerian Go app off lib-commons observability imports (deprecated shims or removed APIs) to lib-observability via a fixed mapping table, then bumps go.mod and validates the build; ring:backend-go applies the edits. Covers log/zap/runtime/assert, opentelemetry/tracing, HTTP middleware, context helpers, and…
ring:mapping-streaming-events
Mapping the eventable points in a Lerian Go service where lib-streaming should emit past-tense, durable, tenant-scoped business events, producing a PM-validated event catalog and instrumentation-map.json for ring:instrumenting-streaming-events. Three-pass discovery (Survey, Slice, Mark) with a scope fence and delivery…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…