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 fivol/claude-make-better --skill systems-reviewgit clone --depth 1 https://github.com/fivol/claude-make-betterWrote 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/fivol/claude-make-better/systems-review)<a href="https://agentmods.dev/skills/fivol/claude-make-better/systems-review"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/systems-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/fivol/claude-make-better/systems-review"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/systems-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 | $0.07943 |
| Opus 5 | $0.00039 | $0.03972 |
| Sonnet 5 | $0.00016 | $0.01589 |
| Haiku 4.5 | $0.00008 | $0.00794 |
Grade A, and why
systems-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 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 — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the main agent for the /systems-review skill. The user invoked you to audit codebase subsystems. Follow this flow exactly.
Inputs
User input is in $ARGUMENTS. Parse in this order:
- Detect flags (any position):
--yes,-y,--auto→ setnon_interactive = true. Strip them from the token list. - The first remaining numeric token →
count. - All other remaining tokens (joined) →
subsystemfilter. - Either
countorsubsystemmay be absent. Defaultnon_interactive = false.
Examples:
8→ count=8, subsystem=none, non_interactive=falseflutter→ count=default, subsystem="flutter", non_interactive=falseflutter 4→ count=4, subsystem="flutter", non_interactive=false--yes 5 flutter→ count=5, subsystem="flutter", non_interactive=true-y→ count=default, subsystem=none, non_interactive=true- (empty) → count=default, subsystem=none, non_interactive=false
Configuration
Load the merged config by running:
bash ${CLAUDE_SKILL_DIR}/bin/load-config.sh
This prints a single JSON object combining built-in plugin defaults with any user override at <repo-root>/.claude/make-better/config.json. All knobs (registry_path, review_stale_after_days, etc.) come from this object. Do not read any config file directly — always go through the loader.
Apply user count only if it is <= max_systems_per_run; otherwise clamp and inform the user.
Standing project instructions
Rules that apply to everything this skill does in the repo. Two optional sources, both applied whenever present:
instructions— array of strings in the merged config (strictly an array; the loader exits with an error otherwise). Areview:section's list replaces the common top-level one rather than extending it — arrays are replaced wholesale, so repeat shared rules if you need both.<repo-root>/.claude/make-better/INSTRUCTIONS.md— free-form markdown._meta.instructions_appliedsays whether it exists; read it from_meta.instructions_path.
What ships with it
14 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.
- bin/load-config.py 4.5 KB runs code
- bin/load-config.sh 432 B runs code
- defaults.json 683 B
- prompts/implement-agent.md 6.3 KB
- prompts/review-agent.md 10 KB
- topics/architecture.md 1.8 KB
- topics/bugs.md 1.4 KB
- topics/completeness.md 5.8 KB
- topics/consistency.md 1.7 KB
- topics/docs-sync.md 1.5 KB
- topics/dry.md 4.4 KB
- topics/efficiency.md 1.6 KB
- topics/security.md 1.6 KB
- topics/tests.md 2.5 KB
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 · 563 lines · 79 tokens per session scan A e4dea8ee9ac9
systems-review is a skill published in the GitHub repository fivol/claude-make-better (5 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 7,943 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…