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 alexmond/alexmskills --skill tune-repogit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/tune-repo)<a href="https://agentmods.dev/skills/alexmond/alexmskills/tune-repo"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/tune-repo/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/alexmond/alexmskills/tune-repo"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/tune-repo.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 | $0.00117 | $0.02049 |
| Opus 5 | $0.00059 | $0.01025 |
| Sonnet 5 | $0.00023 | $0.00410 |
| Haiku 4.5 | $0.00012 | $0.00205 |
Grade A, and why
tune-repo 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 6d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tune-repo
Make a repository a place where Claude Code performs at its best: an accurate CLAUDE.md, a single fast deterministic verification command, enforced static guardrails, and low permission friction. The biggest accuracy killer is a stale CLAUDE.md — a wrong instruction is worse than a missing one — so this skill verifies claims against reality before adding anything.
Run the three phases below. If the user's request contains audit, do Phases 1–2 only and
apply nothing. Make minimal, idiomatic changes; never weaken an existing guardrail; never
invent a convention the repo doesn't already follow.
Calibrate to the project (don't impose a generic template)
Discover the repo's own conventions and match them. If sibling repositories exist in the parent directory, read the closest well-tuned one (the one with the most complete CLAUDE.md + enforced guardrails) and use it as the template, so a fleet of related repos converges on one house style instead of drifting.
Map common stacks to their guardrails and one-shot verify command, but confirm what the repo actually uses before proposing anything:
- Java / Maven or Gradle — formatter (e.g. spring-javaformat / Spotless), Checkstyle, PMD,
and a JaCoCo coverage gate; verify via
mvn verify(often wrapped in ascripts/dev-verify.shthat formats then runs the full build, plus ascripts/dev-test.sh <selector>for one test). Themaven-qualityplugin provides these skills for Java/Maven repos. - JS / TS — Prettier/Biome + ESLint +
tsc --noEmit+ the test runner; verify via the package script that chains them (e.g.npm run check). - Python — ruff/black + mypy + pytest; verify via the project's task runner.
- Go / Rust —
gofmt/vet/golangci-lint+go test;fmt/clippy+cargo test.
For a non-code repo (docs, plugin/marketplace, infra), infer the verify command and guardrails from its own tooling or the closest sibling.
On sibling conflicts, prefer the in-repo working tool. If this repo already uses spring-javaformat and the sibling uses Spotless, the in-repo tool stays — swapping a working guardrail for a different one is churn. Surface the divergence in Phase 2 as a finding for the user to decide, never silently align.
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.
- 6d ago First seen · 145 lines · 117 tokens per session scan A a8452cd527c0
tune-repo is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 2,049 once invoked, about $0.0006 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 2026-09-05.
Other skills, from other repositories
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
ci-pipeline-patterns
GitHub Actions workflow templates, matrix builds, caching, and monorepo CI strategies.
test-fixing
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
ci-pipeline
CI pipeline discipline: lint→build→test→quality→security, fail-fast, deterministic build, secret handling, PR gates.