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 agentmods add skills/hardness1020/leeway/code-reviewnpx skills add hardness1020/Leeway --skill code-reviewgit clone --depth 1 https://github.com/hardness1020/LeewayWhat 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 | $0.00040 | $0.00269 |
| Opus 5 | $0.00020 | $0.00134 |
| Sonnet 5 | $0.00008 | $0.00054 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
code-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 2d 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.
What it actually says
Code Review
Workflow
- Scan structure — use
globandgrepto understand the scope of changes - Read changed files — focus on logic, not formatting
- Check against patterns — see references/checklist.md for the full checklist
- Identify issues — categorize by severity (critical, major, minor, suggestion)
- Write report — structured as Summary, Issues, Suggestions
Rules
- Cite file:line for every issue — evidence before opinion
- Keep one issue per point — don't bundle unrelated problems
- Suggest fixes, not just problems — "consider X" is better than "this is wrong"
- Praise good patterns — reinforce what works
Output Format
## Summary
[1-2 sentence overall assessment]
## Issues
- **[severity]** file:line — description
## Suggestions
- file:line — recommendation
For the full quality checklist, read references/checklist.md.
What ships with it
1 file 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.
- 2d ago First seen · 37 lines · 40 tokens per session scan A 484e0739294b
code-review is a skill published in the GitHub repository hardness1020/Leeway (113 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 269 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 2026-08-30.
Other skills, from other repositories
memory
Persist important outcomes from this step to long-term storage with automatic forgetting curve.
economic-reasoning
Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.
care.basic
Offer basic care check-ins for neighbors.
first_aid.basic
Prepare basic first-aid support and immediate care.
messaging.group
Send a concise practical group update.
safety.respond
Respond to urgent or risky events with safety movement, announcement, and memory.