Borrowing it
Nothing to install: this file belongs to johnreitano/spekka. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/johnreitano/spekka/main/.claude/commands/spekka/customize-skills.mdgit clone --depth 1 https://github.com/johnreitano/spekkaWrote 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/commands/johnreitano/spekka/customize-skills)<a href="https://agentmods.dev/commands/johnreitano/spekka/customize-skills"><img src="https://agentmods.dev/badge/commands/johnreitano/spekka/customize-skills.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 | $0.00000 | $0.00964 |
| Opus 5 | $0.00000 | $0.00482 |
| Sonnet 5 | $0.00000 | $0.00193 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
customize-skills 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customize skills for the project's tech stack
Update the skills under .claude/skills/**/SKILL.md based on well-known best practices for the technologies that comprise this project's tech stack.
CRITICAL EXECUTION REQUIREMENTS:
- Create a TodoWrite list with the 4 phases below BEFORE starting
- Execute phases SEQUENTIALLY - mark each as in_progress ONLY when starting
- IMMEDIATELY after completing ANY phase (including skill work), call TodoWrite to mark it completed
- IMMEDIATELY after marking a phase completed, start the next phase
- If ANY phase fails, STOP and report the failure to the user
- NEVER wait for user input between phases
PHASE 1: Customize skills
The content in the files .claude/skills/**/SKILL.md can be divided into three categories:
- Content that can usefully be updated or extended to be specific to the technologies in this project's tech stack (
spekka/product/tech-stack.md). Update or extend this content in such a way that when subsequently used in a prompt to generate code, the code will comply with the well-known best practices for the relevant technologies. For example, in.claude/skills/global-coding-style/SKILL.md, the generic statement to "Use consistent indentation (spaces or tabs) and configure your editor/linter to enforce it" should be changed to make more specific recommendations for the language(s) used in the project's tech stack. - Content that doesn't need to be customized because it is already applicable, as is, to the tech stack. Leave this content unchanged. For example, this category would include the all of the content in the version control skill (
.claude/skills/global-version-control/SKILL.md) for most projects. - Content that should be removed because it is not applicable to the tech stack. Remove this content. For example, the recommendation to "Use Transactions for Related Changes" in
.claude/skills/backend-queries/SKILL.mdshould be removed for an app that has a first-class design principle of using a read-only database.
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 · 78 lines · 0 tokens per session scan A 48b8b702f8a2
customize-skills is a command published in the GitHub repository johnreitano/spekka (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 964 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.