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 LiozShor/claude-code-skills --skill skill-improvergit clone --depth 1 https://github.com/LiozShor/claude-code-skillsWrote 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/liozshor/claude-code-skills/skill-improver)<a href="https://agentmods.dev/skills/liozshor/claude-code-skills/skill-improver"><img src="https://agentmods.dev/badge/skills/liozshor/claude-code-skills/skill-improver.svg" alt="Measured on agentmods" 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 | $0.00157 | $0.02879 |
| Opus 5 | $0.00078 | $0.01439 |
| Sonnet 5 | $0.00031 | $0.00576 |
| Haiku 4.5 | $0.00016 | $0.00288 |
Grade A, and why
skill-improver 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 7d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Improver
Inspect an existing agent skill and improve it safely. The goal is to make it more reliable, safer, clearer, easier to trigger correctly, and easier to evaluate. Preserve what works. Fix what is vague, risky, missing, or bloated. Do not rewrite aggressively just because you can.
Safety modes
Classify the requested work into one of four modes before touching anything:
- Review-only — read the skill and produce findings. No edits.
- Safe-edit — apply low-risk improvements that preserve intent: clearer wording, sharper trigger description, missing sections, formatting, stronger gotchas, more explicit output format.
- Permission-changing or destructive — ask the user before any change that expands
allowed-tools, deletes files, removes major sections, alters core behavior, renames the skill, moves files, modifies scripts, or splits the skill. - Structural-defect repair — adding missing required frontmatter fields (
name,description,allowed-tools) is not a permission change; it is documentation of behavior the skill already exhibits. Infer the minimum tools the visible workflow uses (shell snippets ⇒Bash; file creates ⇒Write; file edits ⇒Edit). Apply the fix and flag the inference in the diagnosis. Do not block on user approval for adding a missing field — only for expanding a field that is already present.
If the user's request is ambiguous, start in review-only mode and ask before editing.
When this triggers
Reviewing or improving EXISTING skills only. For greenfield skill creation, use skills-build.
Use this skill when the user asks to:
- Check, audit, or review an existing skill or
SKILL.md. - Improve triggers, descriptions, gotchas, gates, output format, or evaluation checklist.
- Review or tighten
allowed-toolspermissions. - Validate folder structure (
references/,assets/,scripts/). - Split an over-broad skill into focused ones.
- Diagnose why a skill is not triggering or is triggering too often.
- Refactor a skill without changing its purpose.
- Audit the whole skill fleet at once ("which skills need work") — run
scripts/survey-skill-fleet.shfirst, then improve the worst offenders.
What ships with it
9 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.
- assets/eval-template.json 791 B
- assets/skill-review-template.md 734 B
- evals/01-review-only-existing-skill.json 705 B
- evals/02-apply-safe-edits.json 1005 B
- evals/03-negative-trigger-create-new.json 531 B
- references/permission-review.md 4.8 KB
- scripts/list-skill-evals.sh 1.5 KB runs code
- scripts/review-skill-structure.sh 6.4 KB runs code
- scripts/survey-skill-fleet.sh 2.0 KB runs code
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.
- 7d ago First seen · 182 lines · 157 tokens per session scan A 5c97ba61e5a5
skill-improver is a skill published in the GitHub repository LiozShor/claude-code-skills (2 stars, last pushed 19d ago), licensed MIT. It adds 157 tokens to every session and 2,879 once invoked, about $0.0008 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.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…